ASE 2026
41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026)

Title Page

Article: ase26foreword-fm000-p (type: Frontmatter) doi:

Welcome from the Chairs

Article: ase26foreword-fm001-p (type: Frontmatter) doi:

ASE 2026 Organization

Article: ase26foreword-fm002-p (type: Frontmatter) doi:

Sponsors

Article: ase26foreword-fm003-p (type: Frontmatter) doi:

Trust the Delta: Rethinking Software Validation in the AI Era (Keynote)
Michael Pradel
(CISPA Helmholtz Center for Information Security, Germany)

Publisher's Version Article: ase26key-key1-p (type: Keynote) doi:10.1145/3832783.3857283

Beyond the Hype: What AI Really Did to Software Engineering (Keynote)
Joost Noppen
(British Telecommunications, UK; King’s College London, UK)

Publisher's Version Article: ase26key-key2-p (type: Keynote) doi:10.1145/3832783.3857284

Lost in Automated Specifications: A Time and Space Odyssey in System Testing (Keynote)
Myra B. Cohen
(Iowa State University, USA)

Publisher's Version Article: ase26key-key3-p (type: Keynote) doi:10.1145/3832783.3857285

SpecFSM: Extracting and Repairing Finite State Machines from Protocol Specification Documents
Xiangdong Li, DaWei Huang, Jingjing Guan, and Hui Li
(Beijing University of Posts and Telecommunications, Beijing, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p13-p (type: Full Paper) doi:10.1145/3832783.3834331

Reproduction Package for “SpecFSM: Extracting and Repairing Finite State Machines from Protocol Specification Documents” (doi:10.5281/zenodo.19239022): This repository contains the code and example artifacts for the paper "SpecFSM: Extracting and Repairing Finite State Machines from Protocol Specification Documents".

Trace-Driven Automated PoC Synthesis for On-Chain Attacks
Xing Su, Hao Wu, Hanzhong Liang, Yunlin Jiang, Yuxi Cheng, Yating Liu, Fengyuan Xu, and Sheng Zhong
(Nanjing University, Nanjing, China)

Publisher's Version Article: ase26main-p24-p (type: Full Paper) doi:10.1145/3832783.3834332

Context-Aware Trust Verification for Identity-Based Software Signing
Chinenye Okafor, James C. Davis, and Santiago Torres-Arias
(Purdue University, USA)

Publisher's Version Published Artifact Artifacts Available Artifacts Functional Article: ase26main-p30-p (type: Full Paper) doi:10.1145/3832783.3834333

	Poster: ASE 2026 Not-in-Person Research paper poster
	DiVerify Presentation Video: ASE 2026 Presentation Video for 'Context-Aware Trust Verification for Identity-Based Software Signing'
	Artifact for "Context-Aware Trust Verification for Identity-Based Software Signing" (doi:10.5281/zenodo.21365072): This artifact contains the implementation and evaluation harness for DiVerify, a system that adds diverse identity verification to Sigstore-based software signing. With DiVerify, a signing identity can be tied to multiple signer scopes. These scopes includes OIDC identity/provider, device fingerprint, hardware ...

A11YRepair: Bridging Web Accessibility Barriers via Knowledge-Enhanced Divide-and-Conquer Repair
Kai Huang, Ling Zhu, Jian Zhang, Xiaofei Xie, and Chunyang Chen
(TU Munich, Germany; Nanyang Technological University, Singapore; Singapore Management University, Singapore)

Publisher's Version Published Artifact Artifacts Available ACM SIGSOFT Distinguished Paper Award Article: ase26main-p37-p (type: Full Paper) doi:10.1145/3832783.3834334

Reproduction Package for Article 'A11YRepair: Bridging Web Accessibility Barriers via Knowledge-Enhanced Divide-and-Conquer Repair' (doi:10.6084/m9.figshare.31896229.v3): The implementation of A11YRepair

GALA: Graph-Augmented LLM Agents for Root Cause Analysis and Incident Response in Microservices
Yifang Tian, Yaming Liu, Zichun Chong, Zihang Huang, Yiran Li, and Hans-Arno Jacobsen
(University of Toronto, Canada)

Publisher's Version Article: ase26main-p46-p (type: Full Paper) doi:10.1145/3832783.3834335

IntOAgent: A Practical Framework for Automated Detection and Triggering of Integer Overflow Vulnerabilities
Yuelin Wang, Jiongchi Yu, Xiaofei Xie, Yaohui Sun, Tianyu Shi, Yanbang Sun, Qiang Hu, and Junjie Wang
(Tianjin University, China; Singapore Management University, Singapore)

Publisher's Version Article: ase26main-p66-p (type: Full Paper) doi:10.1145/3832783.3834336

LLM-Based Agents for Identifying Bug-Introducing Commits
Niklas Risse and Marcel Böhme
(MPI-SP, Germany; CISPA Helmholtz Center for Information Security, Germany)

Publisher's Version Published Artifact Artifacts Available ACM SIGSOFT Distinguished Paper Award Article: ase26main-p90-p (type: Full Paper) doi:10.1145/3832783.3834337

Artifact for "LLM-based Agents for Identifying Bug-Introducing Commits" (doi:10.5281/zenodo.19336272): Full reproduction package for the paper "LLM-based Agents for Identifying Bug-Introducing Commits".

ARMOR: A Robust Self-Supervised Framework for Root Cause Analysis in Microservices under Missing Modality
Wenzhuo Qian, Hailiang Zhao, Ziqi Wang, Zhipeng Gao, Jiayi Chen, Zhiwei Ling, and Shuiguang Deng
(Zhejiang University, China)

Publisher's Version Article: ase26main-p102-p (type: Full Paper) doi:10.1145/3832783.3834338

Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering
Xiuwei Shang, Li Hu, Xiao Jiang, Jieke Shi, Junda He, Zhou Yang, Shaoyin Cheng, Guoqiang Chen, Weiming Zhang, and David Lo
(University of Science and Technology of China, China; Singapore Management University, Singapore; University of Alberta, Canada; Anhui Province Key Laboratory of Digital Security, Hefei, China)

Publisher's Version Article: ase26main-p130-p (type: Full Paper) doi:10.1145/3832783.3834339

Source-Free Detection and Impact Analysis of Compiler Optimization Problems in Mobile Applications
Han Hu, Xiaoheng Xie, Bo Sun, Jian Gu, Gang Fan, and Li Li
(Independent Researcher, Hong Kong; Huawei, China; Monash University, Australia; Beihang University, China)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p135-p (type: Full Paper) doi:10.1145/3832783.3834340

tool for the paper Source-Free Detection and Impact Analysis of Compiler Optimization Problems in Mobile Applications (doi:10.5281/zenodo.21175865): Artifact for the paper "Source-Free Detection and Impact Analysis of Compiler Optimization Problems in Mobile Applications". Contains: - opt-detector.exe: executable detection tool - README: usage instructions and tutorial - RQ2 experimental results (830 Google Play apps, 21,972 native libraries) - RQ3 third-party ...

Quantum Squeeziness: An Information Theoretical Metric for Quantum Software Testability
Avner Bensoussan, Hector Menendez, and Mohammad Reza Mousavi
(King's College London, UK)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p151-p (type: Full Paper) doi:10.1145/3832783.3834341

Artifact of Quantum Squeeziness: Information-Theoretic Foundations of Quantum Software Testability (doi:10.5281/zenodo.21177819): The archive Quantum_Squeeziness_AE_Kit.zip contains all materials required for ASE 2026 Artifact Evaluation. Specifically, it includes: Complete source code Benchmark quantum circuits Precomputed experimental results Docker environment Dependency specifications Documentation Replication scripts for RQ1–RQ3 A copy of ...

Spec2V: Planning-Guided Specification-to-Verilog Generation Framework with Verification-Driven Debugging
Xuming Liu, Chi Zhang, Jinglong Xu, Shan Zhou, and Jinbo Wang
(Technology and Engineering Center for Space Utilization at Chinese Academy of Sciences, China; University of Chinese Academy of Sciences, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p157-p (type: Full Paper) doi:10.1145/3832783.3834342

Spec2V poster: A poster of Spec2V.

Spec2V: Planning-Guided Specification-to-Verilog Generation Framework with Verification-Driven Debugging (doi:10.5281/zenodo.21629619): This artifact provides the implementation and experimental resources of Spec2V: Planning-Guided Specification-to-Verilog Generation Framework with Verification-Driven Debugging. Spec2V is an LLM-based agent framework designed to automatically generate Verilog code from natural language specifications through planning, ...

Characterizing the Landscape of Open-Source Satellite Software
Jinfeng Wen, Qi Liang, Yuehan Sun, Federica Sarro, Ao Zhou, Xuanzhe Liu, and Shangguang Wang
(Beijing University of Posts and Telecommunications, China; University College London, UK; Peking University, China)

Publisher's Version Article: ase26main-p161-p (type: Full Paper) doi:10.1145/3832783.3834343

Bridging the Gap between Intent and Impact: An Empirical Study of GPU Optimizations in Deep Learning Frameworks
Siqi Wang, Fanjing Luo, Xing Hu, Xinyu Wang, and Xin Xia
(Zhejiang University, China; Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, China)

Publisher's Version Article: ase26main-p162-p (type: Full Paper) doi:10.1145/3832783.3834344

CIPIHunter: Detecting Configuration-Induced Prediction Instability in Deep Learning Frameworks
Yanzhou Mu, Shuo Meng, Mijung Kim, Xiang Chen, Chunrong Fang, Zhenyu Chen, and Juan Zhai
(UNIST, Republic of Korea; Nanjing University, China; Nantong University, China; University of Massachusetts at Amherst, USA)

Publisher's Version Article: ase26main-p163-p (type: Full Paper) doi:10.1145/3832783.3834345

TasmScan: Continuation-Aware Taint Analysis for TVM Bytecode with Savelist Abstraction
Yixuan Liu, Yin Wu, and Yi Li
(Nanyang Technological University, Singapore; Xi'an Jiaotong University, China)

Publisher's Version Article: ase26main-p182-p (type: Full Paper) doi:10.1145/3832783.3834346

Quick Bug Detection through Black-Box Checking: A Systematic Evaluation
Bram Pellen, María Belén Rodríguez, Frits Vaandrager, and Petra van den Bos
(Radboud University, Netherlands; University of Twente, Netherlands)

Publisher's Version Published Artifact Artifacts Available Artifacts Functional Article: ase26main-p302-p (type: Full Paper) doi:10.1145/3832783.3834347

Quick Bug Detection Through Black-Box Checking: a Systematic Evaluation (Artifact) (doi:10.5281/zenodo.21389827): This artifact provides the software and data used to obtain the results of the paper “Quick Bug Detection Through Black-Box Checking: a Systematic Evaluation”, which has been accepted for publication at the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026).

A Scalable Rule-Based Deep Reinforcement Learning Framework for the Next Release Problem
Hemanth Gudaparthi, Nan Niu, Prem Swaroopaanda Ramalingam, and Laxman Chowdary Kakara
(Governors State University, USA; University of North Florida, USA)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p350-p (type: Full Paper) doi:10.1145/3832783.3834348

Replication package for the paper entitled, A Scalable Rule-Based Deep Reinforcement Learning Framework for the Next Release Problem (doi:10.5281/zenodo.21382748): This package implements the two-stage GRL (Graph Reinforcement Learning) + DRL (Deep Reinforcement Learning) pipeline described in the paper: a rule-based graph construction stage driven by GPT-2 perplexity/probability signals, followed by an offline Deep Q-Network that learns requirement-selection policies.

DynCA: An Effective Algorithm for 3-Wise Combinatorial Interaction Testing in Highly Configurable Systems
Ruizhi Shi, Shuangyu Lyu, Renyu Yang, Wei Wu, Chanjuan Liu, Chunming Hu, and Chuan Luo
(Beihang University, China; Central South University, China; Dalian University of Technology, China)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p354-p (type: Full Paper) doi:10.1145/3832783.3834349

DynCA: An Effective Algorithm for 3-Wise Combinatorial Interaction Testing in Highly Configurable Systems (Artifact) (doi:10.5281/zenodo.21359991): DynCA is a novel and effective algorithm for solving large-scale 3-wise CCAG problems. This repository provides the implementation of DynCA, the testing instances used in the experiments, and the corresponding experimental results.

Effective and Efficient Context Retrieval via Partial Dependency Graph for Repository-Level Code Generation
Zhongxin Liu, Zhonghao Jiang, Zhifan Ye, Haoye Wang, Jiakun Liu, and Xiaoxue Ren
(Zhejiang University, China; Hangzhou City University, China; Harbin Institute of Technology, China)

Publisher's Version Article: ase26main-p356-p (type: Full Paper) doi:10.1145/3832783.3834350

When Ambiguity Meets Atypicality: Dual-Perspective Test Input Prioritization for DNNs
Haoran Li, Shihai Wang, Bin Liu, Jialuo Chen, Wenjing Zhu, Yu Liu, Tengfei Shi, and Shudi Guo
(Beihang University, China; Zhejiang University, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p367-p (type: Full Paper) doi:10.1145/3832783.3834351

The artifacts of DuFP (doi:10.5281/zenodo.19184936): Reproduction package for the ASE 2026 paper "When Ambiguity Meets Atypicality: Dual-Perspective Test Input Prioritization for DNNs" (DuFP). It contains the Python implementation of DuFP and all experiment scripts (with a README), the pretrained DNN models, and the datasets required to reproduce the reported results. A ...

Not In My Git Yard: Catching Backdoors at Commit and Release Time
Dimitri Kokkonis, Michaël Marcozzi, and Stefano Zacchiroli
(Université Paris-Saclay, France; CEA List, France; Télécom Paris, France; Institut Polytechnique de Paris, France)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p379-p (type: Full Paper) doi:10.1145/3832783.3834352

Artifact for the paper "Not In My Git Yard: Catching Backdoors at Commit and Release Time" (ASE'26) (doi:10.5281/zenodo.21390730): This artifact enables evaluating Lily, a new approach and tool for preventing backdoor injections in the CI and release vetting pipelines. More precisely, this artifact makes it possible to reproduce the evaluation results reported in our ASE'26 paper about Lily, as they are detailed in tables 3–6 of this paper. See ...

EffiHolmes: Differential Profiling-Guided Repository Level Time Inefficiency Fix Localization
Haowen Yang, Yun Peng, and Zishuo Ding
(Hong Kong University of Science and Technology, Guangzhou, China; Chinese University of Hong Kong, Hong Kong)

Publisher's Version Article: ase26main-p417-p (type: Full Paper) doi:10.1145/3832783.3834353

Maximal Format-Free Data Repair
Zijian Luo, Xi Wu, Hong Jin Kang, Alan Fekete, and Rahul Gopinath
(University of Sydney, Australia)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p428-p (type: Full Paper) doi:10.1145/3832783.3834354

Reproduction of Package of Paper "Maximal Format-Free Data Repair" (doi:10.5281/zenodo.21769131): BetaMax is a structured-data repair project for real-world settings where large volumes of data lack explicit format specifications such as regular expressions or grammar files. Unlike existing approaches that depend on format specifications or precise parser error messages, betaMax uses only a set of valid data ...

AgentExecutor: Partial Code Execution via Agentic Context Generation
Junkai Chen, Chengran Yang, Xing Hu, Zhenhao Li, Xin Xia, and David Lo
(Singapore Management University, Singapore; Zhejiang University, China; York University, Canada)

Publisher's Version ACM SIGSOFT Distinguished Paper Award Article: ase26main-p477-p (type: Full Paper) doi:10.1145/3832783.3834355

Automated Lemma Discovery in Agentic Program Verification
Huan Zhao, Haoxin Tu, Zhengyao Liu, Martin C. Rinard, and Abhik Roychoudhury
(National University of Singapore, Singapore; Massachusetts Institute of Technology, USA)

Publisher's Version Article: ase26main-p529-p (type: Full Paper) doi:10.1145/3832783.3834356

Regression Accumulation in Multi-turn LLM Programming Conversations
Yonghui (Andie) Huang, Lin Ma, Amjed Tahir, Qian Zhang, Liwen Xiao, and Lysa Xiao
(Massey University, New Zealand; Alibaba Research Center for Complexity Sciences, China; Hangzhou Normal University, China; University of Otago, New Zealand)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p579-p (type: Full Paper) doi:10.1145/3832783.3834357

Regression Accumulation in Multi-Turn LLM ProgrammingConversations (doi:10.5281/zenodo.20394889): LLM-assisted programming often spans several turns. Each new code suggestion must satisfy the current request without breaking requirements established earlier. We refer to this problem as regression accumulation. We build 542 eight-turn tasks from HumanEval+ and MBPP+ and evaluate six LLMs, producing 26,016 turn ...

TheBotCompany: Self-Organizing Multi-agent Systems for Continuous Software Development
Wenhan Lyu, Yue Xiao, Yixuan Zhang, and Yifan Sun
(William & Mary, USA)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p597-p (type: Full Paper) doi:10.1145/3832783.3834358

TheBotCompany Source Code and Experiment Data (doi:10.5281/zenodo.21775778): Source code of TheBotCompany, and related research projects data conducted for research paper "TheBotCompany: Self-Organizing Multi- Agent Systems for Continuous Software Development"

When Comments Mislead: An Empirical Study of Outdated Comments in LLM-Based Code Completion
Zhikun Xia, Yuan Huang, Xiangping Chen, and Zibin Zheng
(Sun Yat-sen University, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p613-p (type: Full Paper) doi:10.1145/3832783.3834359

Reproduction Package for Article 'When Comments Mislead: An Empirical Study of Outdated Comments in LLM-Based Code Completion' (doi:10.5281/zenodo.19249395): This artifact provides the dataset, implementation, and experimental scripts required to reproduce the results presented in the paper "When Comments Mislead: An Empirical Study of Outdated Comments in LLM-Based Code Completion". The artifact investigates how outdated comments influence LLM-based code completion by ...

Property-Based Testing of Wafer Handling Robots via Model-Based Planning and Fuzzing
Ruiyang Xu, Jingjing Liang, Guoyue Zheng, Geguang Pu, and Ting Su
(East China Normal University, China)

Publisher's Version Article: ase26main-p621-p (type: Full Paper) doi:10.1145/3832783.3834360

ATLAS: Agentic Taxonomy of LArge-Scale Software Ecosystems
Junyi Lu, Mengyao Lyu, Jiahui Wu, Lei Yu, Chengwei Liu, Fengjun Zhang, Li Yang, Chun Zuo, and Yang Liu
(Institute of Software at Chinese Academy of Sciences, China; University of Chinese Academy of Sciences, China; Nanyang Technological University, Singapore; Nankai University, China; Sinosoft, China)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p622-p (type: Full Paper) doi:10.1145/3832783.3834361

ATLAS: Agentic Taxonomy of LArge-Scale Software Ecosystems (doi:10.5281/zenodo.21160280): # Replication package for the paper "ATLAS: Agentic Taxonomy of LArge-Scale Software Ecosystems" ATLAS is a multi-agent LLM framework that automatically constructs hierarchical taxonomies of software repositories at ecosystem scale: a Designer Agent derives data-driven splitting dimensions, a Classifier Agent performs ...

SimServing: Native-Execution Simulation for Evolution-Resilient LLM Serving Configuration Tuning
Yujie Huang, Jiazhen Gu, Zhihan Jiang, and Michael R. Lyu
(Chinese University of Hong Kong, Hong Kong)

Publisher's Version Article: ase26main-p625-p (type: Full Paper) doi:10.1145/3832783.3834362

LLM Agents Can See Code Repositories
Dongjian Ma, Silin Chen, Yufei Yang, Yuling Shi, Yanfu Yan, and Xiaodong Gu
(Shanghai Jiao Tong University, China; Xi'an Jiaotong University, China; Zhejiang University, China)

Publisher's Version Article: ase26main-p734-p (type: Full Paper) doi:10.1145/3832783.3834363

Are Reasoning Traces Faithful in LLM-Based Code Vulnerability Detection?
Jialai Wang, Juncheng Lu, Songtao Yang, Bingyi He, Zeyu Gao, Chao Zhang, and Shuai Wang
(National University of Singapore, Singapore; Tsinghua University, China; Zhongguancun Laboratory, China; Huazhong University of Science and Technology, China; Hong Kong University of Science and Technology, Hong Kong)

Publisher's Version Article: ase26main-p776-p (type: Full Paper) doi:10.1145/3832783.3834364

CtxFuzz: Context-Aware Directed Fuzzing via Runtime Fuzzer-Agent Cooperation
Jiho Kim, Dongkwan Kim, HyungSeok Han, Youngjoon Kim, Soyeon Park, Sangwoo Ji, Joshua Wang, Dae R. Jeong, and Taesoo Kim
(Georgia Institute of Technology, USA; Microsoft, USA; Independent Researcher, USA; Samsung Electronics, Republic of Korea; Seoul National University, Republic of Korea)

Publisher's Version ACM SIGSOFT Distinguished Paper Award Article: ase26main-p797-p (type: Full Paper) doi:10.1145/3832783.3834365

SustainSR: Interpretable OSS Sustainability Prediction via Symbolic Regression
Yang Deng, Mustafa Misir, Jinfu Chen, and Jifeng Xuan
(Wuhan University, China; Duke Kunshan University, China)

Publisher's Version Article: ase26main-p823-p (type: Full Paper) doi:10.1145/3832783.3834366

Stop When It Matters: Detectability-Guided Microbenchmarking for Performance Regression Testing
Zongxiong Chen, Derui Zhu, Jinfu Chen, Kundi Yao, Alexander Pretschner, Weiyi Shang, Manfred Hauswirth, and Sonja Schimmler
(Fraunhofer FOKUS, Germany; Rochester Institute of Technology, USA; Wuhan University, China; Ontario Tech University, Canada; TU Munich, Germany; fortiss, Germany; University of Waterloo, Canada; Technische Universität Berlin, Germany)

Publisher's Version Published Artifact Artifacts Available ACM SIGSOFT Distinguished Paper Award Article: ase26main-p833-p (type: Full Paper) doi:10.1145/3832783.3834367

Reproduction Package for Article "Stop When It Matters: Detectability-Guided Microbenchmarking for Performance Regression Testing" (doi:10.5281/zenodo.21760554): ## Repository Layout - `local-mde.ipynb`: notebook for loading `results/mde-reproduce/**` and reproducing the paper tables and figures. - `results/mde-reproduce/`: cached experiment outputs for the RQs and discussion studies. - `src/`: Python scripts for running experiments, evaluating results, and generating ...

Evolution-Aware Regression Test Prioritization of ML-Enabled Systems using Gradient-Based Behavior Vectors
Eunho Cho, Donghwan Shin, and In-Young Ko
(KAIST, Republic of Korea; University of Sheffield, UK)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p872-p (type: Full Paper) doi:10.1145/3832783.3834368

Replication Kit for 'Evolution-Aware Regression Test Prioritization of ML-Enabled Systems using Gradient-Based Behavior Vectors' (doi:10.6084/m9.figshare.31830196.v5): Replication Kit for 'Evolution-Aware Regression Test Prioritization of ML-Enabled Systems using Gradient-Based Behavior Vectors'

Multi-level Code Optimization via Mixture of Prompts
Yun Peng, Jun Wan, Jiakun Liu, Shuzheng Gao, David Lo, and Xiaoxue Ren
(Fudan University, China; Zhejiang University, China; Harbin Institute of Technology, China; Chinese University of Hong Kong, Hong Kong; Singapore Management University, Singapore; Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, China)

Publisher's Version Article: ase26main-p874-p (type: Full Paper) doi:10.1145/3832783.3834369

Evaluating the Maintainability of ViewModel Tests using Multi-modal DSLs: An Industrial Mixed-Methods Study
Mario Fuksa, Sandro Speth, and Steffen Becker
(University of Stuttgart, Germany; TU Munich, Germany)

Publisher's Version Article: ase26main-p892-p (type: Full Paper) doi:10.1145/3832783.3834370

Sound and Efficient Statistical Model Checking for Probabilities and Bounded Rewards
Hao Bu, Lin Huang, Tao Wei, and Jingyi Wang
(Ant Group, China; Zhejiang University, China)

Publisher's Version Article: ase26main-p914-p (type: Full Paper) doi:10.1145/3832783.3834371

Tracing the Invisible: Semantic Message Flow Discovery via Data Contracts in Real-World Distributed Systems
Youlong Chen, Jie Lu, Mingtao Huang, Chenghang Shi, Yongheng Huang, Haofeng Li, Dong Liu, Mengna Ma, Yong Liu, Qinfen Hao, and Lian Li
(Institute of Computing Technology at Chinese Academy of Sciences, China; University of Chinese Academy of Sciences, China; Zhongguancun Laboratory, China; Qi An Xin Technology Group, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p924-p (type: Full Paper) doi:10.1145/3832783.3834372

Hermes: Artifact for Tracing the Invisible: Semantic Message Flow Discovery via Data Contracts in Real-World Distributed Systems (doi:10.5281/zenodo.21374539): Research artifact accompanying the ASE 2026 paper “Tracing the Invisible: Semantic Message Flow Discovery via Data Contracts in Real-World Distributed Systems.” Hermes discovers semantic message flows in distributed systems by combining static analysis with LLM-assisted analysis of message types as semantic contracts, ...

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study
Zhihao Chen, Ying Zhang, Yi Liu, Gelei Deng, Yuekang Li, Yanjun Zhang, Jianting Ning, Leo Yu Zhang, Lei Ma, and Zhiqiang Li
(Griffith University, Australia; Wake Forest University, USA; Nanyang Technological University, Singapore; University of New South Wales, Australia; Zhejiang Sci-Tech University, China; University of Tokyo, Japan; University of Alberta, Canada; Independent Researcher, China)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p928-p (type: Full Paper) doi:10.1145/3832783.3834373

SkillLeakBench: Artifact for "How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study" (doi:10.5281/zenodo.21154129): SkillLeakBench is the dataset, detection pipeline, and offline reproduction suite accompanying the ASE 2026 paper "How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study." It contains the released dataset, static and dynamic detection components, and scripts for reproducing the paper's dataset, ...

WebCQ: Cooperative Multi-agent Deep Reinforcement Learning for Scalable Web GUI Testing
Yujia Fan, Sinan Wang, Zebang Fei, Yao Qin, Huaxuan Li, and Yepang Liu
(Southern University of Science and Technology, China)

Publisher's Version Published Artifact Artifacts Available Artifacts Functional Article: ase26main-p944-p (type: Full Paper) doi:10.1145/3832783.3834374

	WebCQ Presentation Video: A recorded presentation of WebCQ for ASE 2026.
	WebCQ One-Slide Summary: A one-slide visual summary of WebCQ for ASE 2026.
	WebCQ ASE 2026 Artifact (doi:10.5281/zenodo.21176469): This artifact contains the WebCQ source code, Docker packaging, a prebuilt Docker image, Linux x86_64 Chrome/ChromeDriver binaries, execution scripts, and metric computation scripts. It supports a 10-minute smoke test on Gap and reduced runs for WebCQ and two variants. The artifact is intended to validate the ...

MalSkills: Detecting Malicious Skills in the Agentic Supply Chain via Neuro-symbolic Reasoning
Shenao Wang, Junjie He, Yanjie Zhao, Yayi Wang, Kan Yu, and Haoyu Wang
(Huazhong University of Science and Technology, China; Ant Group, China)

Publisher's Version Article: ase26main-p951-p (type: Full Paper) doi:10.1145/3832783.3834375

Less Is More: Tuning Configurable Systems with Imperfect Fidelity
Yulong Ye, Miqing Li, and Tao Chen
(University of Birmingham, UK)

Publisher's Version Published Artifact Artifacts Available Artifacts Functional ACM SIGSOFT Distinguished Paper Award Article: ase26main-p988-p (type: Full Paper) doi:10.1145/3832783.3834376

Supplementary: Supplementary file

Reproduction Package for Article "Less Is More: Tuning Configurable Systems with Imperfect Fidelity" (doi:10.5281/zenodo.21364961): The artifact provides the reproduction package for the article “Less Is More: Tuning Configurable System with Imperfect Fidelity.” It includes the source code, experimental scripts, configuration files, and result-processing utilities required to reproduce the main experiments reported in the paper. The package also ...

Programming by Chat: A Large-Scale Behavioral Analysis of 11,579 Real-World AI-Assisted IDE Sessions
Ningzhi Tang, Chaoran Chen, Zihan Fang, Gelei Xu, Maria Dhakal, Yiyu Shi, Collin McMillan, Yu Huang, and Toby Jia-Jun Li
(University of Notre Dame, USA; Vanderbilt University, USA)

Publisher's Version Article: ase26main-p1071-p (type: Full Paper) doi:10.1145/3832783.3834377

Understanding Bugs in Modern Agentic Frameworks: A Study of Symptoms, Root Causes, and Triggering Conditions
Xiaowen Zhang, Hannuo Zhang, and Shin Hwei Tan
(Concordia University, Canada)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p1085-p (type: Full Paper) doi:10.1145/3832783.3834378

	slide_ase26main-p1085-p: Slide for the bug study of agentic frameworks
	ase26main-p1085-p: Video presentation about the bug study in modern agentic frameworks
	Understanding Bugs in Modern Agentic Frameworks: A Study of Symptoms, Root Causes, and Triggering Conditions (Artifact) (doi:10.5281/zenodo.21364480): This artifact contains the annotation codebook, labeled dataset, results of the transferability study, and scripts for analyzing input characteristics.

Neuro-symbolic Requirements Elicitation: Utilizing Formal Verification Counterexamples as Contextual Prompts
Okba Tibermacine and Chouki Tibermacine
(National School of Artificial Intelligence, Sidi Abdallah, Algeria; University of Southern Brittany, France)

Publisher's Version Article: ase26main-p1198-p (type: Full Paper) doi:10.1145/3832783.3834379

SmartPoC: Validating Smart Contract Vulnerability Findings through PoC Generation and Execution
Longfei Chen, Ruibin Yan, Taiyu Wong, Yiyang Chen, Jialai Wang, and Chao Zhang
(Tsinghua University, China; Peking University, China; National University of Singapore, Singapore)

Publisher's Version ACM SIGSOFT Distinguished Paper Award Article: ase26main-p1210-p (type: Full Paper) doi:10.1145/3832783.3834380

Every Scenario Matters: Scenario-Guided White-Box Testing for Static Code Checkers Powered by LLMs
Jun Liu, Liqiang Ji, Jiwei Yan, Linjie Pan, Jinsong Ren, Jun Yan, and Jian Zhang
(Institute of Software at Chinese Academy of Sciences, China; University of Chinese Academy of Sciences, China; Beijing Key Laboratory of Intelligent Software Engineering, China; Huawei Technologies, China)

Publisher's Version Article: ase26main-p1253-p (type: Full Paper) doi:10.1145/3832783.3834381

Adaptive Proof Refinement with LLM-Guided Strategy Selection
Minghai Lu, Zhe Zhou, Danning Xie, Songlin Jia, Benjamin Delaware, and Tianyi Zhang
(Purdue University, USA; Meta, USA)

Publisher's Version Article: ase26main-p1291-p (type: Full Paper) doi:10.1145/3832783.3834382

	Full Slides: The complete slides of "Adaptive Proof Refinement with LLM-Guided Strategy Selection".
	One-Slide Presentation: A one-slide presentation for the paper "Adaptive Proof Refinement with LLM-Guided Strategy Selection"

Assessing the Cross-Version Applicability of Java Library Vulnerability Exploits
Zirui Chen, Qi Zhan, Jiayuan Zhou, Xing Hu, Xin Xia, and Xiaohu Yang
(Zhejiang University, China; Queen's University, Canada; Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, China)

Publisher's Version Article: ase26main-p1292-p (type: Full Paper) doi:10.1145/3832783.3834383

TDRepro: A Neurosymbolic Approach to Reproducing Timing-Dependent Flaky Test Failures
Shanto Rahman, Talank Baral, August Shi, and Wing Lam
(University of Texas at Austin, USA; George Mason University, USA)

Publisher's Version ACM SIGSOFT Distinguished Paper Award Article: ase26main-p1337-p (type: Full Paper) doi:10.1145/3832783.3834384

Think Before You Code: Dual Reasoning for the NLSafety–Utility Trade-Off in LLM Code Generation
Honghao Tan, Haibo Wang, and Shin Hwei Tan
(Concordia University, Canada)

Publisher's Version Article: ase26main-p1364-p (type: Full Paper) doi:10.1145/3832783.3834385

Fragmented Markers, Mixed Results: A Systematic Review of AI Coding Assistants and Developer Productivity
Annemarie Wittig, Alina Mailach, and Norbert Siegmund
(Leipzig University, Germany)

Publisher's Version Published Artifact Artifacts Available Artifacts Functional ACM SIGSOFT Distinguished Paper Award Article: ase26main-p1373-p (type: Full Paper) doi:10.1145/3832783.3834386

Supplementary Material to "Fragmented Markers, Mixed Results: A Systematic Review of AI Coding Assistants and Developer Productivity" (doi:10.5281/zenodo.21352349): The artifact provides the complete research materials underlying the systematic literature review, including all collected literature, comprising the candidate papers and the final included paper set. It further provides the intermediate and final datasets covering every analysis stage, including extracted markers, ...

How Reasoning Shapes Social Bias in LLM-Generated Code?
Weifeng Sun, Jieke Shi, Zhou Yang, Yuchen Chen, Hongyan Li, Meng Yan, and David Lo
(Singapore Management University, Singapore; University of Alberta, Canada; Alberta Machine Intelligence Institute, Canada; Nanjing University, China; Chongqing University, China)

Publisher's Version Article: ase26main-p1394-p (type: Full Paper) doi:10.1145/3832783.3834387

From Runnable Code to Shippable Applications: Test-Driven Development for Full-Stack Web Application Generation
Yuxuan Wan, Tingshuo Liang, Jiakai Xu, Jingyu Xiao, Yintong Huo, and Michael R. Lyu
(Chinese University of Hong Kong, Hong Kong; Columbia University in the City of New York, USA; Singapore Management University, Singapore)

Publisher's Version Article: ase26main-p1397-p (type: Full Paper) doi:10.1145/3832783.3834388

Planner-Fuzz: Overcoming Diagnostic Saturation in UAV Planners via Boundary-Oriented Fuzzing
Rongbo Chen, Chengcheng Zhao, Peng Cheng, Jiming Chen, and Taegyu Kim
(Zhejiang University, China; Pennsylvania State University, USA)

Publisher's Version Article: ase26main-p1399-p (type: Full Paper) doi:10.1145/3832783.3834389

Automated Assertion Generation and Regression Testing for Machine Learning Notebooks
Yingao (Elaine) Yao, Vedant Nimje, Varun Viswanath, and Saikat Dutta
(Cornell University, USA; Veermata Jijabai Technological Institute, India; Dwarkadas J Sanghvi College of Engineering, India)

Publisher's Version Published Artifact Artifacts Available ACM SIGSOFT Distinguished Paper Award Article: ase26main-p1451-p (type: Full Paper) doi:10.1145/3832783.3834390

Testing jupyter notebook (doi:10.5281/zenodo.21149272): NBTest is a tool that automatically generates assertions/tests for machine-learning Jupyter notebooks, and tests those notebooks using the generated assertions. This repository is the research artifact accompanying our paper *"Automated Assertion Generation and Regression Testing for Machine Learning Notebooks"* ...

Learning the Lexical Structure of Black-Box Systems by Parsing Systematic String Edit Mutations
Moeketsi Raselimo, Lars Grunske, and Bernd Fischer
(Humboldt University of Berlin, Germany; Stellenbosch University, South Africa)

Publisher's Version ACM SIGSOFT Distinguished Paper Award Article: ase26main-p1479-p (type: Full Paper) doi:10.1145/3832783.3834391

KQFuzz: Knowledge-Guided Fuzzing for Quantum Libraries via Large Language Models
Fuyuan Xia, Qixin Zhang, Chenhao Ying, Haojin Zhu, Shuai Wang, Yuan Luo, Pingchuan Ma, and Yuxuan Du
(Shanghai Jiao Tong University, China; Nanyang Technological University, Singapore; Hong Kong University of Science and Technology, Hong Kong; Zhejiang University of Technology, China)

Publisher's Version ACM SIGSOFT Distinguished Paper Award Article: ase26main-p1509-p (type: Full Paper) doi:10.1145/3832783.3834392

	KQFuzz One-Slide Presentation: A one-slide presentation of KQFuzz for ASE 2026.
	KQFuzz Presentation Video: A recorded presentation of KQFuzz for ASE 2026.

What Breaks When LLMs Code? Characterizing Operational Safety Failures of Agentic Code Assistants
Alif Al Hasan and Sumon Biswas
(Case Western Reserve University, USA)

Publisher's Version Published Artifact Artifacts Available Artifacts Functional Article: ase26main-p1517-p (type: Full Paper) doi:10.1145/3832783.3834393

Appendix: Appendix

Artifact: What Breaks When LLMs Code? Characterizing Operational Safety Failures of Agentic Code Assistants (doi:10.5281/zenodo.21151511): This is the artifact accompanying our ASE 2026 paper. It provides the code used to mine, filter, and annotate real-world operational safety failures of agentic code assistants (from GitHub issues) and to build the accompanying literature review (from academic databases), plus the coding manual used in the paper.

When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents
Zesen Liu, Zhixiang Zhang, Yuchong Xie, and Dongdong She
(Hong Kong University of Science and Technology, China; Fudan University, China)

Publisher's Version Published Artifact Artifacts Available ACM SIGSOFT Distinguished Paper Award Article: ase26main-p1531-p (type: Full Paper) doi:10.1145/3832783.3834394

Source code of COMA (doi:10.5281/zenodo.19248854): Artifact for the paper "When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents".

ExplainBench: Evaluating Code Explanations from Agents
Zhiyuan Pan, Sungmin Kang, Imam Nur Bani Yusuf, and Abhik Roychoudhury
(Zhejiang University, China; National University of Singapore, Singapore)

Publisher's Version Article: ase26main-p1571-p (type: Full Paper) doi:10.1145/3832783.3834395

Finding Typing-Related Bugs in JVM Implementations
Yanzhou Lu, Junjie Chen, Yingquan Zhao, Tianchang Gao, and Zan Wang
(Tianjin University, China)

Publisher's Version Article: ase26main-p1588-p (type: Full Paper) doi:10.1145/3832783.3834396

Compressing Code Context for LLM-Based Issue Resolution
Haoxiang Jia, Earl T. Barr, and Sergey Mechtaev
(Peking University, China; University College London, UK)

Publisher's Version Article: ase26main-p1597-p (type: Full Paper) doi:10.1145/3832783.3834397

When Dependencies Depend: A Large-Scale Study on Conditional Dependencies and Their Security Implications in C/C++
Yifeng Di, Juewei Zhang, and Tianyi Zhang
(Purdue University, USA; Carnegie Mellon University, USA)

Publisher's Version Article: ase26main-p1654-p (type: Full Paper) doi:10.1145/3832783.3834398

Towards Fully Automated Medical Imaging Code Generation via Validation-Based Context Engineering
Zixiao Zhao, Jing Sun, Zhe Hou, Cheng-Hao Cai, Qian Liu, Mengze Li, Zijian Zhang, and Jin Song Dong
(University of Auckland, New Zealand; Griffith University, Australia; Monash University, Suzhou, China; Beijing Institute of Technology, China; National University of Singapore, Singapore)

Publisher's Version Article: ase26main-p1668-p (type: Full Paper) doi:10.1145/3832783.3834399

From Plan to Action: How Well Do Agents Follow the Plan?
Shuyang Liu, Saman Dehghan, Jatin Ganhotra, Martin Hirzel, and Reyhaneh Jabbarvand
(University of Illinois at Urbana-Champaign, USA; IBM, USA)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p1675-p (type: Full Paper) doi:10.1145/3832783.3834400

Reproduction package and raw trajectories for Article `From Plan to Action: How Well Do Agents Follow the Plan?` (doi:10.5281/zenodo.22047054): This artifact accompanies “From Plan to Action: How Well Do Agents Follow the Plan?” It contains 21,120 recorded SWE-agent trajectories spanning four language models, two benchmarks (SWE-bench Verified and SWE-bench Pro), and eight plan settings. The package includes plan configurations, trajectory-processing and ...

Needle in the Repo: Diagnosing Maintainability Failures in AI-Generated Repository Edits
Haichao Zhu, Qian Zhang, Jiyuan Wang, Zhaorui Yang, and Yuxin Qiu
(Qualcomm, USA; University of California at Riverside, USA; Tulane University, USA)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p1701-p (type: Full Paper) doi:10.1145/3832783.3834401

Artifacts for Diagnosing Maintainability Failures (doi:10.5281/zenodo.21154293): This artifact provides the benchmark cases, evaluation infrastructure, and supporting materials for Needle in the Repo. It enables reproducible evaluation of AI coding agents on software maintainability tasks, including both functional correctness and maintainability-oriented criteria.

An Empirical Study of Data Access Practice in Android AR Apps to Understand User Privacy Risks
Sabbir Hussain Meraj, Long Trac, Xiaoyin Wang, Xusheng Xiao, and Wei Wang
(University of Texas at San Antonio, USA; Arizona State University, USA)

Publisher's Version Published Artifact Artifacts Available Artifacts Functional ACM SIGSOFT Distinguished Paper Award Article: ase26main-p1726-p (type: Full Paper) doi:10.1145/3832783.3834402

Artifact for: An Empirical Study of Data Access Practice in Android AR Apps to Understand User Privacy Risks (doi:10.5281/zenodo.21753818): This artifact accompanies our paper, "An Empirical Study of Data Access Practice in Android AR Apps to Understand User Privacy Risks," accepted at the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE'26). It contains the complete pipeline source code, the full list of all 179 apps analyzed ...

Clarity Is Not Assumed: Understanding LLM-Based Code Generation under Ambiguous Requirements
Di Yang, Xinou Xie, Xiuwen Yang, Ming Hu, Yihao Huang, Yueling Zhang, Weikai Miao, Ting Su, Chengcheng Wan, and Geguang Pu
(East China Normal University, China; Shanghai Innovation Institute, China)

Publisher's Version Published Artifact Artifacts Available ACM SIGSOFT Distinguished Paper Award Article: ase26main-p1878-p (type: Full Paper) doi:10.1145/3832783.3834403

One-slide Presentation: A one-slide presentation for the paper "Clarity Is Not Assumed: Understanding LLM-Based Code Generation under Ambiguous Requirements."

Orchid: Artifact for “Clarity Is Not Assumed: Understanding LLM-Based Code Generation under Ambiguous Requirements” (doi:10.6084/m9.figshare.32899583.v3): Orchid is a benchmark for evaluating LLM-based code generation under ambiguous requirements. Built on HumanEval and BigCodeBench, it contains 1,304 function-level Python tasks covering lexical ambiguity, syntactic ambiguity, semantic ambiguity, and vagueness. It provides original and ambiguous prompts, ambiguity ...

Conflict Extraction in Probabilistic Datalog Analyses
Siyu Chen, Chungha Sung, Xuyang Li, and Jingbo Wang
(Purdue University, USA; Amazon Web Services, USA)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p1888-p (type: Full Paper) doi:10.1145/3832783.3834404

Conflict Extraction in Probabilistic Datalog Analyses (doi:10.5281/zenodo.21776435): Artifact of the paper Conflict Extraction in Probabilistic Datalog Analyses, including code, as well as benchmark pipelines.

EMERGE: Checking Implementation Equivalence for LLMs via Rule Synthesis
Qi Zhan, Xing Hu, Xin Xia, and Shanping Li
(Zhejiang University, China; Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, China)

Publisher's Version Article: ase26main-p1924-p (type: Full Paper) doi:10.1145/3832783.3834405

	EMERGE One-Slide Summary: A one-slide visual summary of EMERGE.
	EMERGE Presentation Video: A recorded presentation of EMERGE.

SpecTrum: Specification-Guided Differential Fuzzing for Ethereum Consensus Clients
Seokhun Jeong, Gyeongmin Dan, Sukyoung Ryu, and Sungjae Hwang
(KAIST, Republic of Korea; Sungkyunkwan University, Republic of Korea)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p1970-p (type: Full Paper) doi:10.1145/3832783.3834406

Artifacts of SpecTrum: Specification-Guided Differential Fuzzing for Ethereum Consensus Clients (doi:10.5281/zenodo.21389903): Research artifact for the paper "SpecTrum: Specification-Guided Differential Fuzzing for Ethereum Consensus Clients" (ASE 2026). It contains Consensus-SpecTec, the test generator, the differential testing harness, and the scripts for reproducing the experiments.

Where Does Balance Break? Boundary Discovery for Game Balance Testing under a Finite Simulation Budget
Hiroki Mukai, Yusaku Kato, Norihiro Yoshida, Erina Makihara, and Katsuro Inoue
(Ritsumeikan University, Japan)

Publisher's Version Published Artifact Artifacts Available Artifacts Functional Article: ase26main-p2013-p (type: Full Paper) doi:10.1145/3832783.3834407

Replication Package for "Where Does Balance Break? Boundary Discovery for Game Balance Testing under a Finite Simulation Budget" (doi:10.5281/zenodo.21076109): Replication package for the paper "Where Does Balance Break? Boundary Discovery for Game Balance Testing under a Finite Simulation Budget", accepted at ASE 2026. Contains source code, experiment data, notebooks, and a verification script for reproducing and checking Tables 1–4 and Figures 2–3. See README.md in the ...

On the Effects of Customized Configurations of Static Code Analysis Tools: A Prospective Cohort Study of SonarQube Cloud
Sabato Nocera, Sira Vegas, and Giuseppe Scanniello
(University of Salerno, Italy; Polytechnic University of Madrid, Spain)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p2032-p (type: Full Paper) doi:10.1145/3832783.3834408

On the Effects of Customized Configurations of Static Code Analysis Tools: A Prospective Cohort Study of SonarQube Cloud - Artifact (doi:10.6084/m9.figshare.31842262.v3): This artifact contains the data and scripts of the paper "On the Effects of Customized Configurations of Static Code Analysis Tools: A Prospective Cohort Study of SonarQube Cloud."

RefineAct: Automatic Runtime Verification of LLM Agent Actions
Fraol Batole, Foutse Khomh, and Hridesh Rajan
(Tulane University, USA; Polytechnique Montréal, Canada)

Publisher's Version ACM SIGSOFT Distinguished Paper Award Article: ase26main-p2301-p (type: Full Paper) doi:10.1145/3832783.3834409

Video Presentation: This is a video presentation for our paper titled "RefineAct: Automatic Runtime Verification of LLM Agent Actions".

Verifier-in-the-Loop LLM Solving of Heap Constraints for Concolic Execution
Shaoran Xia, Leyi Cheng, Caihua Dong, Dongdong She, Bo Wang, Xin Peng, and Zhen Dong
(Fudan University, China; Soochow University, China; Hong Kong University of Science and Technology, China; Beijing Jiaotong University, China)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p2302-p (type: Full Paper) doi:10.1145/3832783.3834410

COHEC (doi:10.6084/m9.figshare.31868686.v1): This deposit packages COHEC, a research prototype that extends JDart (concolic execution on NASA Java PathFinder) with a verifier-in-the-loop, LLM-based multi-agent solver for high-level heap and type constraints over reference-typed inputs. When JDart encounters constraints that Z3 cannot discharge, it delegates them ...

RealAIGC: Towards More Realistic Evaluation of AI-Generated Code Detection in Real-World Code Repository
Wentao Chen, Yufei Chen, Huiqun Yu, Guisheng Fan, Kaiwen Zhi, Peite Guo, and Jianyuan Yu
(East China University of Science and Technology, China; Shanghai Engineering Research Center of Smart Energy, China)

Publisher's Version ACM SIGSOFT Distinguished Paper Award Article: ase26main-p2317-p (type: Full Paper) doi:10.1145/3832783.3834411

Hybrid Fuzzing in Input Generation Logic
Siwei Wei, Shihao Zhu, Ruijie Meng, and Yan Cai
(Institute of Software at Chinese Academy of Sciences, China; University of Chinese Academy of Sciences, China; National University of Singapore, Singapore)

Publisher's Version ACM SIGSOFT Distinguished Paper Award Article: ase26main-p2343-p (type: Full Paper) doi:10.1145/3832783.3834412

Understanding the Code and Architectural Smells Generated by LLMs and Autonomous Agents
Yuecai Zhu, Nikolaos Tsantalis, and Peter C. Rigby
(Concordia University, Canada)

Publisher's Version Article: ase26main-p2377-p (type: Full Paper) doi:10.1145/3832783.3834413

Toward Inclusive Programming Support for Novice Programmers with Dyslexia: Insights from a Comparative Study
Zihan Fang, Janice Chung, Ruijia Chen, Marcia Barnes, Yuhang Zhao, and Yu Huang
(Vanderbilt University, USA; University of Wisconsin-Madison, USA)

Publisher's Version Article: ase26main-p2412-p (type: Full Paper) doi:10.1145/3832783.3834414

AEG-Edit: Bridging API Evolution and Code Semantics for Accurate API Usage in Code Generation
Yitong Lin, Haoye Tian, Dehai Zhao, Chao Ni, Xiaohu Yang, and Xiaoxue Ren
(Zhejiang University, China; Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, China; Aalto University, Finland)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p2449-p (type: Full Paper) doi:10.1145/3832783.3834415

AEG-Edit: Bridging API Evolution and Code Semantics for Accurate API Usage in Code Generation (doi:10.5281/zenodo.21608506): Code and Data for AEG-Edit: Bridging API Evolution and Code Semantics for Accurate API Usage in Code Generation

ReqEvolve: User-Oriented Software Self-Evolution through Automatic Requirement Interpretation
Md Asif Iqbal Fahim and Alessio Ferrari
(University College Dublin, Ireland; National Research Council, Italy)

Publisher's Version Article: ase26main-p2528-p (type: Full Paper) doi:10.1145/3832783.3834416

	ReqEvolve: Presentation Video (ASE 2026): Narrated presentation video (10 min, 1920x1080 MP4, H.264/AAC) for the ASE 2026 paper "ReqEvolve: User-Oriented Software Self-Evolution through Automatic Requirement Interpretation" (Md Asif Iqbal Fahim and Alessio Ferrari), provided in place of an in-person talk. It covers the 13 talk slides: the vision of ...
	ReqEvolve: One-Slide Presentation (ASE 2026): One-slide summary of the ASE 2026 research paper "ReqEvolve: User-Oriented Software Self-Evolution through Automatic Requirement Interpretation" (Md Asif Iqbal Fahim and Alessio Ferrari), submitted in place of an in-person talk. The slide states the key message (a need expressed in plain language as a user story is ...

Testing IFrame Rendering in Web Browsers
Dahyeon Park, Yuseok Jeon, Seongil Wi, and Mijung Kim
(UNIST, Republic of Korea; Korea University, Republic of Korea)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p2611-p (type: Full Paper) doi:10.1145/3832783.3834417

Reproduction Package for Article 'Testing IFrame Rendering in Web Browsers' (doi:10.6084/m9.figshare.33112562.v1): This artifact contains source code and results used in paper. Please refer to the readme.md in the file. This includes the results of ICheck for 5.2 Effectiveness of Test Oracles 5.3 Effectiveness of Bug Detection Capability 5.4 Effectiveness of Input Reduction Capability 5.5 Ablation Study 5.6 Case Studies for ...

Real-World Perturbation Testing of Autonomous Driving Systems
Stefano Carlo Lambertenghi, Matthias Weil, and Andrea Stocco
(TU Munich, Germany; fortiss, Germany)

Publisher's Version Article: ase26main-p2645-p (type: Full Paper) doi:10.1145/3832783.3834418

SwiftGram: Dynamic Lexical Forking for Precise and Efficient Grammar-Constrained Decoding
Shuyi Ling, Liangyi Kang, Jie Liu, Shuai Wang, Zhirou Ma, and Dan Ye
(Institute of Software at Chinese Academy of Sciences, China)

Publisher's Version Article: ase26main-p2654-p (type: Full Paper) doi:10.1145/3832783.3834419

GraphLedger: Repository-Level Vulnerability Detection via Graph-Based Compression and Assumption Validation
Thi-Hong-Cuc Le, Hoang-Quoc-Bao Hua, and Xuan-Bach Le
(Ho Chi Minh City University of Technology - Vietnam National University Ho Chi Minh City, Vietnam)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p2655-p (type: Full Paper) doi:10.1145/3832783.3834420

GraphLedger: Repository-Level Vulnerability Detection via Graph-Based Compression and Assumption Validation (Artifact) (doi:10.5281/zenodo.21356624): GraphLedger is a static-analysis framework that detects security vulnerabilities at the repository level by combining graph-based context compression (Adaptive Assumption-Corroborating Compression, AACC) with monotonic assumption-ledger verification. This artifact contains the full source code and unit tests, dataset ...

Escaping the Self-Repair Trap: Improving Test Oracle Generation via Dual-Context Awareness
Kefan Li, Hongyue Yu, and Yuan Yuan
(Beihang University, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p2670-p (type: Full Paper) doi:10.1145/3832783.3834421

Escaping the Self-Repair Trap: Improving Test Oracle Generation via Dual-Context Awareness (Artifact) (doi:10.5281/zenodo.21357436): This artifact provides the implementation of DCAware, a dynamic-context-aware test oracle generation method. It includes the source code, scripts for static context extraction, LLM-based test generation, pass-rate evaluation, mutation testing, and result printing.

PSearch: Search-Based Patch Generation in the Era of LLM-Based Automated Program Repair
Haichuan Hu, Ye Shang, Weifeng Sun, and Quanjun Zhang
(Nanjing University of Science and Technology, China; Nanjing University, China; Singapore Management University, Singapore)

Publisher's Version Article: ase26main-p2681-p (type: Full Paper) doi:10.1145/3832783.3834422

Same Scrutiny, More Time: Eye Tracking Insights into Reviewing LLM-Labelled Code
Ranim Khojah, Francisco Gomes de Oliveira Neto, Mazen Mohamad, Julian Frattini, and Philipp Leitner
(Chalmers University of Technology, Sweden; University of Gothenburg, Sweden; RISE Research Institutes of Sweden, Sweden)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable ACM SIGSOFT Distinguished Paper Award Article: ase26main-p2693-p (type: Full Paper) doi:10.1145/3832783.3834423

Replication package for the paper "Same Scrutiny, More Time: Eye Tracking Insights into Reviewing LLM-Labelled Code" (doi:10.5281/zenodo.21180198): Material used in the study including processed data as well as all scripts and configuration files needed to conduct the statistical data analysis.

Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks
Yuchen Chen, Wei Cheng, Yuan Xiao, Weisong Sun, Chunrong Fang, Yang Liu, Zhenyu Chen, and Baowen Xu
(Nanjing University, China; Nanjing University of Aeronautics and Astronautics, China; Nanyang Technological University, Singapore)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p2706-p (type: Full Paper) doi:10.1145/3832783.3834424

ARIA (doi:10.5281/zenodo.21770429): This artifact provides the reproduction package for ARIA, including source code, prompt templates, experimental configurations, data-processing and evaluation scripts, and reproduction instructions. It supports reproduction of the main experiments and further research on the security of customized LLMs for coding.

On the Reliability of Code Comprehension Proxies
Erfan Arvan, Nadeeshan De Silva, Oscar Chaparro, and Martin Kellogg
(New Jersey Institute of Technology, USA; William & Mary, USA)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable ACM SIGSOFT Distinguished Paper Award Article: ase26main-p2877-p (type: Full Paper) doi:10.1145/3832783.3834425

	AppendixA: Appendix A: Secondary Analyses
	Replication Package for: On the Reliability of Code Comprehension Proxies (doi:10.5281/zenodo.21218362): This artifact contains the data, scripts, web application, and study materials used in the paper "On the Reliability of Code Comprehension Proxies." It supports full reproduction of all analyses, figures, and tables reported in the paper.

Discovering Performance Archetypes: Critical-Path-Aware Pattern Analysis and Regression Detection
Kaveh Shahedi, Heng Li, Maxime Lamothe, and Foutse Khomh
(Polytechnique Montréal, Canada)

Publisher's Version ACM SIGSOFT Distinguished Paper Award Article: ase26main-p2896-p (type: Full Paper) doi:10.1145/3832783.3834426

Video Presentation: A video presentation introducing a critical-path-aware approach to discovering performance archetypes and detecting performance regressions in software systems.

Barista: Synthesizing Typestate Specifications with LLM Agents
Catarina Gamboa, Paulo Canelas, Ricardo Costa, Márcio Caetano, Jonathan Aldrich, and Alcides Fonseca
(Carnegie Mellon University, USA; University of Lisbon, Portugal)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p2950-p (type: Full Paper) doi:10.1145/3832783.3834427

Artifact for 'Barista: Synthesizing Typestate Specifications with LLM Agents' (doi:10.6084/m9.figshare.31865314.v1): Artifact: Barista is the replication package for a paper on synthesizing typestate specifications using LLM agents. It contains the Barista tool, an agentic pipeline that transforms Java API documentation into LiquidJava typestate specifications using four specialized Claude-based agents. The package includes ...

A Longitudinal Study of Android Apps Signing Key Protection
Mark Huasong Meng, Qing Zhang, Weirao Lu, and Chunyang Chen
(University College Dublin, Ireland; JD Group, China; TU Munich, Germany)

Publisher's Version Article: ase26main-p3058-p (type: Full Paper) doi:10.1145/3832783.3834428

Clarity: From Formal System Designs to Verified RL Controllers
Austin O'Quinn, Conor Snedeker, Max Taylor, Lance Joneckis, and Christopher Stewart
(Ohio State University, USA; Boise State University, USA; Idaho National Lab, USA)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p3070-p (type: Full Paper) doi:10.1145/3832783.3834429

CLARITY - Artifact (doi:10.5281/zenodo.21126107): This artifact contains an end-to-end, fully automated workflow for generating the main results of the paper CLARITY, to appear in ASE 2026. This document first describes how to use the artifact to reproduce the main results appearing in the paper. Then, it describes how each step in CLARITY's pipeline can be manually ...

Towards Verifiable Fairness Testing: Auditable Coverage over Data-Supported Input Domains
Yingqian Guo, Wentian Zhao, and Tian Song
(Beijing Institute of Technology, China)

Publisher's Version Published Artifact Artifacts Available ACM SIGSOFT Distinguished Paper Award Article: ase26main-p3140-p (type: Full Paper) doi:10.1145/3832783.3834430

	Poster of SDFDIR: Conference poster for the paper "Towards Verifiable Fairness Testing: Auditable Coverage over Data-Supported Input Domains".
	SDFDIR — One-Page Summary Slide: A one-slide summary of the presentation, intended for display during the Research Papers session, summarizes our paper’s core contributions.
	SDFDIR Presentation Video: A recorded presentation of SDFDIR
	Artifact for "Towards Verifiable Fairness Testing: Auditable Coverage over Data-Supported Input Domains" (doi:10.5281/zenodo.21773348): The replication package for this paper, including the source code, experimental scripts, configuration files, and supporting materials required to reproduce the reported results, is publicly archived on this repository.

PL4SA: Optimized Partial Library Selection for Efficient Static Analysis
Guohao Feng, Yifei Lu, and Minxue Pan
(Nanjing University, China)

Publisher's Version Article: ase26main-p3256-p (type: Full Paper) doi:10.1145/3832783.3834431

VeriSBOM: Secure and Verifiable SBOM Sharing via Zero-Knowledge Proofs
Gianpietro Castiglione, Shahriar Ebrahimi, and Narges Khakpour
(Newcastle University, UK)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p3290-p (type: Full Paper) doi:10.1145/3832783.3834432

VeriSBOM Artifact (doi:10.5281/zenodo.21372814): The artifact contains the code for the VeriSBOM's prototype and experiments.

Bifrost: Empowering Pretrained Language Model with Fallibility Representation for Log-Based Fault Diagnosis
Minghua He, Tong Jia, Lingzhe Zhang, Chiming Duan, Xinlong Zhao, Leyi Pan, Cheng Wang, Kangjin Wang, Yinghao Yu, Liping Zhang, Yifan Wu, and Ying Li
(Peking University, China; Tsinghua University, China; Alibaba Group, China)

Publisher's Version Article: ase26main-p3295-p (type: Full Paper) doi:10.1145/3832783.3834433

All or Nothing: How Library Type Annotations Affect Client-Side Errors in Python
Eric Asare, Luca Di Grazia, and Sarah Nadi
(New York University Abu Dhabi, United Arab Emirates; University of St. Gallen, Switzerland)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p3300-p (type: Full Paper) doi:10.1145/3832783.3834434

Replication Package for All or Nothing: How Library Type Annotations Affect Client-Side Errors in Python (doi:10.6084/m9.figshare.31892497.v2): This artifact contains scripts, datasets, and experimental pipelines for All or Nothing: How Library Type Annotations Affect Client-Side Errors in Python If you only want to reproduce the main results, READ starter.md and start with the Questions Folder. Additional details are provided in the starter.md for full ...

Tensor-Based Batch Fuzzing with Adaptive Perturbation Scaling for Deep Neural Networks
Guanqin Zhang and Yulei Sui
(University of New South Wales, Australia)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p3318-p (type: Full Paper) doi:10.1145/3832783.3834435

Artifact for ``Tensor-Based Batch Fuzzing with Adaptive Perturbation Scaling for Deep Neural Networks'' Expand (doi:10.6084/m9.figshare.33002297.v2): Reproducing Paper Results for ``Tensor-Based Batch Fuzzing with Adaptive Perturbation Scaling for Deep Neural Networks'' in ASE 2026

ChangeWiki: Repository-Level Change Summarization Augmented with Architecture Semantics
Zijun Wang, Wuxia Jin, Jiale Li, Zhanhong Mou, and Ting Liu
(Xi'an Jiaotong University, China)

Publisher's Version Article: ase26main-p3335-p (type: Full Paper) doi:10.1145/3832783.3834436

	ASE2026 ChangeWiki Poster: Poster used for the ASE 2026 Not-in-Person presentation of “ChangeWiki: Repository-Level Change Summarization Augmented with Architecture Semantics”.
	ASE2026 ChangeWiki One Slide: one-slide presentationa one-slide presentation that will be shown during one of the ASE 2026 conference sessions of ChangeWiki: Repository-Level Change Summarization Augmented with Architecture Semantics
	ASE2026 ChangeWiki Presentation Video: Video presentation for ASE ’26 - Recorded presentation of the paper “ChangeWiki: Repository-Level Change Summarization Augmented with Architecture Semantics”

Refine2Diff: Detecting Protocol Specification–Implementation Inconsistencies via Specification-Driven Code Refinement
Yuekun Wang, Lili Quan, and Xiaofei Xie
(Singapore Management University, Singapore)

Publisher's Version Article: ase26main-p3339-p (type: Full Paper) doi:10.1145/3832783.3834437

Free Is More: Empowering Software Agents via Issue-Free Trajectory Learning and Entropy-Aware RLVR Training
Xin-Cheng Wen, Binbin Chen, Haoxuan Lan, Hang Yu, Peng Di, and Cuiyun Gao
(Ant Group, China; Zhejiang University, China; University of New South Wales, Australia; Chinese University of Hong Kong, China)

Publisher's Version Article: ase26main-p3466-p (type: Full Paper) doi:10.1145/3832783.3834438

	ASE-SWE-Fuse Video: ASE-SWE-Fuse Video used at the presentation on ASE 2026
	ASE-SWE-Fuse PPT: ASE-SWE-Fuse PPT used at the presentation on ASE 2026

How Quantum Bugs Live and Die: A Lifecycle-Based Empirical Study of Bugs in Quantum Software
Yasai Shi, Xiangxin Meng, Xiangjie Huang, Jian Zhang, Tianyu Wo, and Xu Wang
(Beihang University, China)

Publisher's Version Article: ase26main-p3477-p (type: Full Paper) doi:10.1145/3832783.3834439

Automated Table Reproduction via Code Generation
Doehyun Baek and Michael Pradel
(CISPA Helmholtz Center for Information Security, Germany)

Publisher's Version Published Artifact Artifacts Available Artifacts Functional Article: ase26main-p3621-p (type: Full Paper) doi:10.1145/3832783.3834440

Reproduction Package for the paper "Automated Table Reproduction via Code Generation" (doi:10.6084/m9.figshare.31860751.v3): This artifact contains code and data used for the paper "Automated Table Reproduction via Code Generation".

MicroAgent: Context-Augmented Multi-agent Framework for Automatic Microservice Decomposition
Zishan Su, Junjie Huang, Shiwen Shan, Xingyan Chen, Hui Zeng, Yuxin Su, Yanlin Wang, and Michael R. Lyu
(Chinese University of Hong Kong, China; Sun Yat-sen University, China)

Publisher's Version Published Artifact Artifacts Available ACM SIGSOFT Distinguished Paper Award Article: ase26main-p3640-p (type: Full Paper) doi:10.1145/3832783.3834441

Artifact for paper "MicroAgent: Context-Augmented Multi-Agent Framework for Automatic Microservice Decomposition" (ASE'26) (doi:10.5281/zenodo.19250602): This is the artifact for the ASE'26 paper, entitled "MicroAgent: Context-Augmented Multi-Agent Framework for Automatic Microservice Decomposition". ## Directory Structure 1. ```graph/``` contains the code for extracting class-level context. 2. ```microagent/``` contains the code for running the multi-agent framework. ...

Optimization-Free Repair of Code LLMs: A Closed-Form Fisher-Guided Bayesian Approach
Zhiyu Duan, Chong Bian, Yizhuo Zhang, and Shunkun Yang
(Beihang University, China; China Mobile, China)

Publisher's Version Article: ase26main-p3860-p (type: Full Paper) doi:10.1145/3832783.3834442

Pattern over Pixels: Measuring Pattern Completion Bias in Multimodal Code Generation
Khai-Nguyen Nguyen, Oscar Chaparro, and Antonio Mastropaolo
(William & Mary, USA)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p3922-p (type: Full Paper) doi:10.1145/3832783.3834443

Replication package for the ASE 2026 paper "Pattern over Pixels: Measuring Pattern Completion Bias in Multimodal Code Generation". (doi:10.5281/zenodo.21388129): The artifact provides Pattern2Code, a benchmark that tests whether multimodal LLMs follow localized visual evidence or complete a repeated UI pattern when generating front-end code from screenshots, together with everything needed to rebuild the benchmark and reproduce the paper's results.

GPU-Accelerated Belief Propagation for Program Analysis
Haoyu Feng and Xin Zhang
(Peking University, China)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p4025-p (type: Full Paper) doi:10.1145/3832783.3834444

GPU-Accelerated Belief Propagation for Program Analysis (Artifact) (doi:10.5281/zenodo.21188278): This artifact packages the implementation and evaluation materials for the paper. It provides a prebuilt Docker environment containing FastLBP, a GPU-accelerated belief propagation framework for program analysis, together with the Wu et al. and PGMax baseline implementations, benchmark data, and scripts for ...

Inferring the Shape of Data Frames in R Programs using Abstract Interpretation
Oliver Gerstl, Florian Sihler, and Matthias Tichy
(Ulm University, Germany)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p4457-p (type: Full Paper) doi:10.1145/3832783.3834445

Reproduction Package: Inferring the Shape of Data Frames in R Programs using Abstract Interpretation (doi:10.5281/zenodo.23010495): This is the artifact (reproduction package) of the research paper "Inferring the Shape of Data Frames in R Programs using Abstract Interpretation", accepted at the ASE 2026. The research paper is available at the DOI [10.1145/3832783.3834445](https://doi.org/10.1145/3832783.3834445). This artifact contains: - the ...

Translation Tag Team: Formal Rules and LLMs Translate More Macros Together Than Apart
Brent Pappas, Joseph Zalusky, Zachary Burkett, and Paul Gazzillo
(University of Central Florida, USA)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p5-p (type: Full Paper) doi:10.1145/3832783.3837412

Artifact for Paper, "Translation Tag Team: Formal Rules and LLMs Translate More Macros Together Than Apart" (doi:10.5281/zenodo.21798007): This artifact contains the MacroBench macro translation benchmark, the MerC macro translation tool, scripts for running MerC and LLMs on MacroBench's macro translation test cases, and all translations and validation results reported in the associated paper.

ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction
Haoyu Wang, Christopher M. Poskitt, Jiali Wei, and Jun Sun
(Singapore Management University, Singapore; Xi'an Jiaotong University, China)

Publisher's Version Article: ase26main-p53-p (type: Full Paper) doi:10.1145/3832783.3837413

Tangent: An Empirical Study of Testing Practices for LLM-Based Agent Applications
Rangeet Pan, Tyler Stennett, Divya Sankar, Bridget McGinn, Alessandro Orso, Raju Pavuluri, Saurabh Sinha, and Maja Vukovic
(IBM Research, USA; Georgia Institute of Technology, USA; University of Georgia, USA)

Publisher's Version Article: ase26main-p87-p (type: Full Paper) doi:10.1145/3832783.3837414

A Unified Model for Cross-Domain Clone Detection via Model Merging
Palash R. Roy, Banani Roy, Kevin A. Schneider, and Chanchal K. Roy
(University of Saskatchewan, Canada)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p92-p (type: Full Paper) doi:10.1145/3832783.3837415

A Unified Model for Cross-Domain Clone Detection via Model Merging (doi:10.5281/zenodo.21209512): The package reproduces the full study: fine-tuning specialist code encoders, merging them into a single cross-domain clone detector with several parameter-level and architecture-level methods (including WUDI-Merging), evaluating on three clone-detection benchmarks, and comparing against a large-language-model baseline.

Don’t Retest Everything: Auditable Regression Scoping for Safety-Critical Systems
Francesco Basciani, Daniele Masti, Patrizio Pelliccione, Alberto Petrucci, Franco Raimondi, Emerson Sales, and Paolo Serri
(Gran Sasso Science Institute, Italy; Gran Sasso Tech, Italy; Thales Alenia Space Italia, Italy)

Publisher's Version Article: ase26main-p115-p (type: Full Paper) doi:10.1145/3832783.3837416

Recovering Revisions of Pull Requests with Altered History
Gengyi Sun, Georges Aaron Randrianaina, Tao Xiao, Yasutaka Kamei, and Shane McIntosh
(University of Waterloo, Canada; Kyushu University, Japan)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p120-p (type: Full Paper) doi:10.1145/3832783.3837417

Recovering Revisions of Pull Requests with Altered History (doi:10.5281/zenodo.21410986): Scripts and data that produce the results in the paper "Recovering Revisions of Pull Requests with Altered History"

Making Theft Useless: Adulteration-Based Protection of Proprietary Knowledge Graphs in GraphRAG Systems
Weijie Wang, Peizhuo Lv, Yan Wang, Weiqing Huang, Rujie Dai, Guokun Xu, Qiujian Lv, Hangcheng Liu, Hao Hu, and Jiaheng Zhang
(Institute of Information Engineering at Chinese Academy of Sciences, China; University of Chinese Academy of Sciences, China; Nanyang Technological University, Singapore; Beijing University of Technology, China; Henan Key Laboratory of Information Security, China; National University of Singapore, Singapore)

Publisher's Version Article: ase26main-p131-p (type: Full Paper) doi:10.1145/3832783.3837418

	Poster: poster of the paper
	Poster: Poster of the paper

Decompiling the Web: Automated Semantic Recovery of Post-compilation Abstraction Leaks
Shriyans Sudhi and Yinxi Liu
(Rochester Institute of Technology, USA)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p145-p (type: Full Paper) doi:10.1145/3832783.3837419

Decompiling the Web: Automated Semantic Recovery of Post-Compilation Abstraction Leaks (doi:10.5281/zenodo.21829401): This artifact accompanies the paper “Decompiling the Web: Automated Semantic Recovery of Post-compilation Abstraction Leaks”. It contains the JS Recon semantic-recovery tool, containerized execution environments, deterministic test applications, a fixed white-box evaluation dataset, sanitized derived results from the ...

AutoSQL: Extracting SQL Templates from Imperative ORM Code in Large-Scale Repositories
Junsong Pu, Yichen Li, Zhuangbin Chen, Zhihan Jiang, and Zibin Zheng
(Sun Yat-sen University, Zhuhai, China; Chinese University of Hong Kong, Hong Kong)

Publisher's Version Article: ase26main-p169-p (type: Full Paper) doi:10.1145/3832783.3837420

SIMD-Accelerated Sparse Bit-Vectors for Pointer Analysis
Zhaoyang Tan, Peisen Yao, and Kui Ren
(Zhejiang University, China)

Publisher's Version Article: ase26main-p176-p (type: Full Paper) doi:10.1145/3832783.3837421

DesignFix: Context-Augmented Repair of Design Rule Violations
Mainul Hossain and Thomas D. LaToza
(George Mason University, USA)

Publisher's Version Article: ase26main-p184-p (type: Full Paper) doi:10.1145/3832783.3837422

LaMAR: Latent Multi-agent Collaboration via KV-Cache Communication for Automated Program Repair
Rui Jiao, Yue Zhang, Zhexuan Feng, and Jinku Li
(Xidian University, China; Shandong University, China)

Publisher's Version Article: ase26main-p198-p (type: Full Paper) doi:10.1145/3832783.3837423

Enhancing Trace-Based Root Cause Analysis for Microservice Systems via Code Change Understanding
Min Zhang, Chenxi Zhang, Senyu Xie, Shihong Chen, Lei Wu, and Xin Peng
(Xidian University, China; Fudan University, China; McDonald's, China)

Publisher's Version Article: ase26main-p199-p (type: Full Paper) doi:10.1145/3832783.3837424

Assessing Uncertainty in Performance Modeling: Conformal Prediction vs. Bayesian Regression
Stefan Jahns, Johannes Dorn, Max Weber, Sven Apel, and Norbert Siegmund
(Leipzig University, Germany; Saarland University, Germany; ScaDS.AI, Germany)

Publisher's Version Article: ase26main-p207-p (type: Full Paper) doi:10.1145/3832783.3837425

RACE-Bench: A Reasoning-Augmented Benchmark for Repository-Level Code Agents on Feature Addition
Shuhan Liu, Zhiyi Zhao, Xing Hu, Kui Liu, Xiaohu Yang, and Xin Xia
(Zhejiang University, China; Independent Researcher, China; Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, China)

Publisher's Version Article: ase26main-p208-p (type: Full Paper) doi:10.1145/3832783.3837426

How Effective Are NPM Malicious Package Detectors? A Large-Scale Empirical Study
Wenbo Guo, Zhongwen Chen, Zhengzi Xu, Chengwei Liu, Ming Kang, Shiwen Song, Chengyue Liu, Yijia Xu, Weisong Sun, and Yang Liu
(Nanyang Technological University, Singapore; Sichuan University, China; Imperial Global Singapore, Singapore; Nankai University, China; Singapore Management University, Singapore)

Publisher's Version Article: ase26main-p218-p (type: Full Paper) doi:10.1145/3832783.3837427

Localizing Data Annotation Faults in Semantic Segmentation Systems
Pengyi Yang, Teng Long, Zhiwu Xu, and Linhai Jing
(China University of Geosciences (Beijing), China; Shenzhen University, China)

Publisher's Version Article: ase26main-p227-p (type: Full Paper) doi:10.1145/3832783.3837428

“Impossible to Hide Secret ...”: Uncovering Security and Privacy Issues in LLM-Native IDEs
Mostafijur Rahman Akhond, Md Afif Al Mamun, Gias Uddin, and Song Wang
(York University, Canada; University of Calgary, Canada)

Publisher's Version Article: ase26main-p234-p (type: Full Paper) doi:10.1145/3832783.3837429

Smart Contract Synthesis via Multi-modal Specifications
Tanglin Chen, Haoxian Chen, Huilin Xiang, and Yuepeng Wang
(ShanghaiTech University, China; Simon Fraser University, Canada)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p244-p (type: Full Paper) doi:10.1145/3832783.3837430

SmartSpec Artifact: Smart Contract Synthesis via Multi-Modal Specifications (doi:10.5281/zenodo.21333365): This reproducibility artifact accompanies the article "Smart Contract Synthesis via Multi-Modal Specifications." It contains the SmartSpec synthesis implementation, 27 smart-contract benchmarks, pre-computed synthesis outputs, scripts for reproducing the reported metrics, a concrete-versus-symbolic ...

BDiff: Block-Aware and Accurate Text-Based Code Differencing
Yao Lu, Wanwei Liu, Tanghaoran Zhang, Kang Yang, Yang Zhang, Wenyu Xu, Longfei Sun, Xinjun Mao, Shuzheng Gao, and Michael R. Lyu
(National University of Defense Technology, China; Chinese University of Hong Kong, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p251-p (type: Full Paper) doi:10.1145/3832783.3837431

BDiff Experimental Dataset: Block-aware and Accurate Text-based Code Differencing (doi:10.6084/m9.figshare.31896472.v1): The repository is organized into three core directories, with the following structure: ├── dataset/ Experimental dataset (real-world code change cases) │ ├── GhJava/ Real code change cases for Java language │ ├── GhPython/ Real code change cases for Python language │ └── GhXML/ Real code change cases for XML language ...

PCodeTrans: Translate Decompiled Pseudocode to Trace-Level Equivalent Source Code
Yuxin Cui, Zeyu Gao, Siliang Qin, Yuanda Wang, Jiaming Wang, Xize Luo, Peng Zhou, and Chao Zhang
(Tsinghua University, China; Institute of Information Engineering at Chinese Academy of Sciences, China; Peking University, China; Hunan University, China)

Publisher's Version Article: ase26main-p256-p (type: Full Paper) doi:10.1145/3832783.3837432

AlphaCu: A Transformation-Driven Synthesis Framework for LLM-Based GPU Kernel Generation
Yangjie Zhou, Xing Ma, Zihan Liu, Qing Wang, Weihao Cui, Wu Sun, Hanjing Wang, Binhang Qi, Jingwen Leng, Yun Lin, Minyi Guo, and Jin Song Dong
(National University of Singapore, Singapore; Shanghai Jiao Tong University, China; Shanghai Qi Zhi Institute, China; Nanjing University, China; Harvard University, USA)

Publisher's Version Article: ase26main-p287-p (type: Full Paper) doi:10.1145/3832783.3837433

How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair
Ramtin Ehsani, Irene Manotas, Saurabh Pujar, Luca Buratti, and Preetha Chatterjee
(Drexel University, USA; IBM Research, USA)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p306-p (type: Full Paper) doi:10.1145/3832783.3837434

Replication Package for 'How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair' (doi:10.5281/zenodo.21381449): This repository contains all data, annotations, and analysis scripts used in our study: How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair.

Mind the Gap: Do Widely-Used SAST Tools Really Cover the Language-Specific Top CWEs?
Zhilin Li, Yiran Nie, Xianglong Qi, Jiwei Yan, and Jun Yan
(Institute of Software at Chinese Academy of Sciences, China; University of Chinese Academy of Sciences, China; Hangzhou Institute for Advanced Study at University of Chinese Academy of Sciences, Hangzhou, China; Beijing University of Technology, China; Beijing Key Laboratory of Intelligent Software Engineering, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p316-p (type: Full Paper) doi:10.1145/3832783.3837435

Dataset for article "Mind the Gap: Do SAST Tools Cover High-Frequency CWEs across Programming Languages?" (doi:10.5281/zenodo.19122421): This repository contains the data, evaluation criteria, and experimental results for the research paper: "Mind the Gap: Do SAST Tools Cover High-Frequency CWEs across Programming Languages?". This study presents a large-scale empirical analysis of nine popular Static Application Security Testing (SAST) tools to ...

Smart Brain: Semantic Anomaly Detection for Operational Time Series in Large Scale Service Systems
Hang Cui, Zexin Wang, Jingjing Li, Juncheng Hu, Haotian Si, Cenjie Hu, Quan Zhou, Yongchang Hu, Lei Han, Dan Pei, Changhua Pei, and Gaogang Xie
(University of Chinese Academy of Sciences, China; Computer Network Information Center at Chinese Academy of Sciences, China; Jilin University, China; Independent Researcher, China; Shenyang Institute of Automation at Chinese Academy of Sciences, China; Beijing Academy of Science and Technology, China; Huawei Technologies, China; Tsinghua University, China)

Publisher's Version Article: ase26main-p337-p (type: Full Paper) doi:10.1145/3832783.3837436

AgentChaos: Chaos Engineering for Agent Systems via Programmatic Fault Injection
Gou Tan, Zhensu Sun, Jieke Shi, Ting Zhang, Zilong He, Qingfu Wu, Shuai Liang, Weifeng Sun, Junda He, Pengfei Chen, Chuanfu Zhang, Lwin Khin Shar, and David Lo
(Sun Yat-sen University, Guangzhou, China; Singapore Management University, Singapore; Monash University, Australia; China Unicom Software Research Institute, Beijing, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p355-p (type: Full Paper) doi:10.1145/3832783.3837437

Artifact of Paper "AgentChaos: Chaos Engineering for Agent Systems via Programmatic Fault Injection" (doi:10.5281/zenodo.21823973): Artifact of Paper "AgentChaos: Chaos Engineering for Agent Systems via Programmatic Fault Injection" in ASE 2026 We propose AgentChaos, a chaos engineering framework for controlled, runtime, non-intrusive LLM API fault injection.

Precise and Efficient Static Data Race Detection
Pei Wang, Zhihang Sun, and Fei He
(Tsinghua University, China; Key Laboratory for Information System Security, China; Beijing National Research Center for Information Science and Technology, China)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p369-p (type: Full Paper) doi:10.1145/3832783.3837438

The artifacts of DEAGLE-DR (doi:10.5281/zenodo.21775785): It is the artifact of our paper 'Precise and Efficient Static Data Race Detection'. It contains the source code, executable binaries, scripts, benchmark data, and result-processing scripts required to reproduce the experimental results presented in our paper.

Best-Effort GR(1) Synthesis: Exploiting Environmental Cooperation under Unrealizability
Sirui Liu, Yating Zhang, Chi Hu, and Wei Dong
(National University of Defense Technology, China; China Academy of Engineering Physics, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p372-p (type: Full Paper) doi:10.1145/3832783.3837439

	One-Slide Presentation: A one-slide presentation for the paper "Best-Effort GR(1) Synthesis: Exploiting Environmental Cooperation under Unrealizability".
	Artifact for Paper: Best Effort GR(1) Synthesis (doi:10.5281/zenodo.21361735): The artifact of this article includes the implementation of the best-effort GR(1) synthesis method we proposed in the Spectra GR(1) synthesizer, the GR(1) benchmark corpus for evaluation, all the scripts required to reproduce the experiment, the raw data for our performance measurements, and detailed documentation ...

TELLER: Non-intrusive Cross-Layer Root-Cause Analysis for LLM Inference
Ruilin Xu, Junyi Li, Pengfei Chen, and Zongxuan Xie
(Sun Yat-sen University, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p423-p (type: Full Paper) doi:10.1145/3832783.3837440

The TELLER Dataset (doi:10.6084/m9.figshare.33142493.v1): Dataset and code of the ASE '26 paper: "TELLER: Non-intrusive Cross-Layer Root-Cause Analysis for LLM Inference".

Predicate-Guided Synthesis of Input Generators via Gentoo
Vasudev Vikram and Rohan Padhye
(Carnegie Mellon University, USA)

Publisher's Version Article: ase26main-p430-p (type: Full Paper) doi:10.1145/3832783.3837441

DepUpgrade: Automating Dependency Upgrade through State-Path Exploration
Xiangxi Ma, Yifan An, Wentong Tian, Xuanqi Wang, Qingao Dong, Xiang Gao, and Hailong Sun
(Beihang University, China)

Publisher's Version Article: ase26main-p442-p (type: Full Paper) doi:10.1145/3832783.3837442

PWCC: Probability-Weighted Combinatorial Coverage for Risk-Informed Scenario Testing of Autonomous Systems
Borhaneddine Hamadou, Chokri Mraidha, and Nikolaos Matragkas
(Université Paris-Saclay, France; CEA List, France)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p443-p (type: Full Paper) doi:10.1145/3832783.3837443

Replication Package for Article "PWCC: Probability-Weighted Combinatorial Coverage for Risk-Informed Scenario Testing of Autonomous Systems" (doi:10.5281/zenodo.21739211): This replication package contains the complete implementation of Probability-Weighted Combinatorial Coverage (PWCC), a risk-informed test adequacy criterion for scenario-based testing of autonomous systems, together with all data, models, and scripts needed to reproduce every result in the paper. Components: (1) the ...

Lost in Translation, Found in Summary: Summary-Driven Supervision for Cross-Language Code Retrieval
Zhijie Liu, Yisi Liu, Linxi Jiang, Yutian Tang, Lili Xiao, and Zhipeng Xue
(Independent Researcher, China; Donghua University, China; University of Glasgow, UK; Zhejiang University, China)

Publisher's Version Article: ase26main-p479-p (type: Full Paper) doi:10.1145/3832783.3837444

ExeCRE: Execution-Consistency Guided Reliability Estimation for Self-Correcting Code Generation
Yiru Dong, Richong Zhang, Fanshuang Kong, and Si Chen
(Beihang University, China)

Publisher's Version Article: ase26main-p496-p (type: Full Paper) doi:10.1145/3832783.3837445

DAGGER: Dynamic Agentic Graph-Guided Efficient Reasoner for Container Image Dependency Optimization
Shikhar Vashistha and Neetesh Kumar
(IIT Roorkee, India)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p522-p (type: Full Paper) doi:10.1145/3832783.3837446

Code for ASE'26 DAGGER for Artifact Evaluation (doi:10.5281/zenodo.21667115): Artifact: DAGGER — Dynamic Agentic Graph-Guided Efficient Reasoner for Container Image Dependency Optimization Paper: Accepted at the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026), Research Track. Authors: Shikhar Vashistha, Neetesh Kumar — Indian Institute of Technology Roorkee, ...

RamFuzz: LLM-Guided Greybox Fuzzing for Spatial Memory Corruption via Valid Range Violation
Shangzhi Xu, Wei Song, Yuekang Li, Nan Sun, Muhammad Ejaz Ahmed, Willy Susilo, Benjamin Turnbull, Xiao Cheng, and Siqi Ma
(University of New South Wales, Australia; CSIRO's Data61, Australia; University of Wollongong, Australia; Macquarie University, Australia)

Publisher's Version Article: ase26main-p540-p (type: Full Paper) doi:10.1145/3832783.3837447

To Ban or Not to Ban? How Open Source Projects Govern GenAI Contributions
Wenhao Yang, Runzhi He, and Minghui Zhou
(Peking University, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p575-p (type: Full Paper) doi:10.1145/3832783.3837448

Replication Package for "To Ban or Not to Ban? How Open Source Projects Govern GenAI Contributions" (doi:10.6084/m9.figshare.31861390.v1): This replication package accompanies the ASE 2026 paper "To Ban or Not to Ban? How Open Source Projects Govern GenAI Contributions." It contains the frozen 67-case corpus of public GenAI governance materials from open source projects, project metadata, RQ1 and RQ2 codebooks, adjudicated case-level coding outputs, ...

GraphDroid: Asynchronous LLM-Based Mobile App GUI Testing via History-Aware Exploration and Hybrid Intent Fulfillment
Xiaolei Li, Jialun Cao, Zhijian Hou, Yuzhi Zhao, Yepang Liu, and Shing-Chi Cheung
(Hong Kong University of Science and Technology, China; Southern University of Science and Technology, China; Guangzhou HKUST Fok Ying Tung Research Institute, China; City University of Hong Kong, China)

Publisher's Version Article: ase26main-p609-p (type: Full Paper) doi:10.1145/3832783.3837449

	Presentation video: Presentation video.
	Poster: Poster for not-in-person attendance.

VARIES: Verification Harness Synthesis and Efficient Scheduling for Unsoundness Detection in Rust Libraries
Huan Li, Xing Hu, Xin Xia, and Xinyu Wang
(Zhejiang University, China; Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, China)

Publisher's Version Article: ase26main-p638-p (type: Full Paper) doi:10.1145/3832783.3837450

Prism: A Multi-solution Reasoning and Synthesis Framework for Repository-Level Issue Resolution
Yibo Wang, Guotian Wang, Zhihao Peng, Ying Wang, Chang Xu, and Zhiliang Zhu
(Northeastern University, China; Nanjing University, China)

Publisher's Version Article: ase26main-p663-p (type: Full Paper) doi:10.1145/3832783.3837451

RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists
Yuexi Yang, Alyssa Wu, Ji Luo, Richeng Xuan, Zhichao Hu, Yuhong Liu, and Zhen Qin
(Zhejiang University, China; Tencent, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p676-p (type: Full Paper) doi:10.1145/3832783.3837452

Replication Package for Paper "RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists" (doi:10.5281/zenodo.21775827): This is the replication package for the paper "RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists".

RFC2TLA+: Extracting and Verifying Formal Models from RFC Documents using Continuous LLM Feedback
Guozhen Ding, Kexin Li, Ilya Grishchenko, and David Lie
(University of Toronto, Canada)

Publisher's Version Published Artifact Artifacts Available Artifacts Functional Article: ase26main-p683-p (type: Full Paper) doi:10.1145/3832783.3837453

Reproduction Package for RFC2TLA+ (doi:10.5281/zenodo.23063101): The reproduction package to reproduce the result in paper RFC2TLA+: Extracting and Verifying Formal Models from RFC Documents using Continuous LLM Feedback.

It Takes Two to Tango: Accelerating Code Generation via Cache-Inspired Hierarchical Speculative Decoding
Yinggang Qiu, Shangwen Wang, Yihao Qin, Mingyang Geng, and Dezun Dong
(National University of Defense Technology, China; Information Support Force Engineering University, China)

Publisher's Version Article: ase26main-p691-p (type: Full Paper) doi:10.1145/3832783.3837454

poster of CacheCoder (ase26main-p691-p): A poster present the work "It Takes Two to Tango: Accelerating Code Generation via Cache-Inspired Hierarchical Speculative Decoding". It includes the background and motivation, the overall method design and the main experimental results, including overall performance, ablation studies, and generalization results.

One Is Not Enough: The Untold Story of Multiple Security Patches for One Vulnerability
Fangyuan Zhang, Lyuye Zhang, Lingling Fan, Chengwei Liu, Yinan Li, Liang Huang, Yang Liu, Zheli Liu, and Sen Chen
(Nankai University, China; Nanyang Technological University, Singapore; Qi An Xin Technology Group, China)

Publisher's Version Article: ase26main-p694-p (type: Full Paper) doi:10.1145/3832783.3837455

Not as Sweet by Another Name: An Empirical Study of Format Robustness in LLM Document Workflows
Xiaoyu Zhang, Xianyun Cheng, Tianlin Li, Yuwei Zheng, Yue Yang, and Yang Liu
(Nanyang Technological University, Singapore; National University of Singapore, Singapore; Beihang University, China; Xi'an University of Architecture and Technology, China)

Publisher's Version Article: ase26main-p718-p (type: Full Paper) doi:10.1145/3832783.3837456

RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks
Jinjun Huang, Zhongzhen Wen, Tongtong Xu, Meng Yan, Xin Xia, and Zhongxin Liu
(Zhejiang University, China; Nanjing University, China; Huawei, China; Chongqing University, China)

Publisher's Version Article: ase26main-p721-p (type: Full Paper) doi:10.1145/3832783.3837457

From Guessing to Seeing: Enhancing LLM-Based Program Repair via Trace-Guided Multi-strategy Debate
Jiaqing Wu, Tong Wu, Manqing Zhang, Yunwei Dong, and Bo Shen
(Northwestern Polytechnical University, China)

Publisher's Version Article: ase26main-p732-p (type: Full Paper) doi:10.1145/3832783.3837458

When Extensions Lie: Large-Scale Study of Privacy Policy Compliance in Browser Extensions
Zilun Wang, Zeyang Zhuang, Mingxue Zhang, Wei Meng, and Michael R. Lyu
(Chinese University of Hong Kong, China; Zhejiang University, China; Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, China)

Publisher's Version Article: ase26main-p741-p (type: Full Paper) doi:10.1145/3832783.3837459

MultiKernelBench: A Multi-platform Benchmark for Kernel Generation
Zhongzhen Wen, Yinghui Zhang, Zhong Li, Zhongxin Liu, Linna Xie, and Tian Zhang
(Nanjing University, China; Zhejiang University, China)

Publisher's Version Article: ase26main-p755-p (type: Full Paper) doi:10.1145/3832783.3837460

Post-quantum Cryptography in the Wild: Assessing the Readiness of Open-Source Ecosystems
Tongxin Yuan, Zhanpeng Liu, Jiashuo Liang, Zhuosheng Zhang, Gongshen Liu, Yang Yu, and Guancheng Li
(Shanghai Jiao Tong University, China; Tencent Xuanwu Lab, China)

Publisher's Version Article: ase26main-p758-p (type: Full Paper) doi:10.1145/3832783.3837461

CodeFault: Predicting Fault Risks from Code Changes via Multi-modal Learning
Yifan Xiao, Shijie Li, and Yu Huang
(Peking University, China; China Southern Power Grid, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p759-p (type: Full Paper) doi:10.1145/3832783.3837462

	CodeFault: Presentation Video (ASE 2026): Pre-recorded presentation (9 min 48 s) of the ASE 2026 paper "CodeFault: Predicting Fault Risks from Code Changes via Multi-modal Learning" for the not-in-person track. Just-in-time defect prediction sees a code change but no runtime behaviour; log-based anomaly detection sees runtime symptoms but only after the ...
	CodeFault: Predicting Fault Risks from Code Changes via Multi-modal Learning - Replication Package (ASE 2026) (doi:10.5281/zenodo.21700762): Replication package for the ASE 2026 paper "CodeFault: Predicting Fault Risks from Code Changes via Multi-modal Learning" (paper ase26main-p759-p, article DOI 10.1145/3832783.3837462).

ReLog: Execution-Aware Logging with Runtime Feedback for LLM-Oriented Debugging
Xin Wang, Yang Feng, Xiaoqian Jiao, Yang Zhang, Zhenhao Li, and Zishuo Ding
(Hong Kong University of Science and Technology, Guangzhou, China; Hebei University of Science and Technology, China; York University, Canada)

Publisher's Version Article: ase26main-p769-p (type: Full Paper) doi:10.1145/3832783.3837463

Documentation vs. Code Patterns: What Drives LLM-Based Exception Oracle Generation?
Soneya Binta Hossain, Matthew B. Dwyer, and Tasfia Tasnim
(University of Texas at Dallas, USA; University of Virginia, USA)

Publisher's Version Article: ase26main-p773-p (type: Full Paper) doi:10.1145/3832783.3837464

Harnessing Uncertainty in Code Language Models: Lessons from Vulnerability Detection
Haodong Li, Xiao Cheng, Xudong Wang, Zhihao Guo, and Haoyu Wang
(Huazhong University of Science and Technology, China; Macquarie University, Australia; Zhongguancun Institute of Artificial Intelligence, China; University of Technology Sydney, Australia)

Publisher's Version Article: ase26main-p786-p (type: Full Paper) doi:10.1145/3832783.3837465

Breaking the Isolation: Coordinated Multi-agent Fuzzing for Smart Contracts with Multi-dimensional Objective Learning
Ruichao Liang, Ruochen Cao, Jing Chen, Kun He, Yebo Feng, Yue Xue, and Cong Wu
(Wuhan University, China; Nanyang Technological University, Singapore; MetaTrust Labs, Singapore)

Publisher's Version Article: ase26main-p791-p (type: Full Paper) doi:10.1145/3832783.3837466

HyTri: Hybrid Triage of CI Failures via LLM Guided Semantic Reasoning and Change Attribution
Lior Broide, Argaman Mordoch, and Roni Stern
(Ben-Gurion University of the Negev, Israel)

Publisher's Version Article: ase26main-p811-p (type: Full Paper) doi:10.1145/3832783.3837467

Latent Reuse in Agent Skills: Multi-modal Clone Detection at Ecosystem Scale
Jiaying Zhu, Lyuye Zhang, Wenbo Guo, and Yang Liu
(Nanyang Technological University, Singapore; Nankai University, China)

Publisher's Version Article: ase26main-p820-p (type: Full Paper) doi:10.1145/3832783.3837468

Specification-Guided Synthesis of Deadlock-Free Communication Protocol Refinements with Large Language Models
Yang Li, Ping Hou, and Nobuko Yoshida
(University of Oxford, UK)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p825-p (type: Full Paper) doi:10.1145/3832783.3837469

Syntropy Artifact (doi:10.5281/zenodo.22030843): This artifact accompanies the ASE'26 paper Specification-Guided Synthesis of Deadlock-Free Communication Protocol Refinements with Large Language Models. It provides the complete software, datasets, Docker environments, experimental scripts, and evaluation pipelines required to reproduce the experimental results ...

Execution-as-Configuration: Security Smells in Model Configuration Artifacts
Mohammed Latif Siddiq, Prince Noah Johnson, and Joanna C. S. Santos
(University of Notre Dame, USA)

Publisher's Version Article: ase26main-p830-p (type: Full Paper) doi:10.1145/3832783.3837470

Evidence-Grounded Logic Vulnerability Detection for Smart Contracts via Runtime Context Reasoning
Guang Gong, Yucong Jiang, Rong Jian, Xiaotao Feng, Zhihan Wei, Qi Li, and Ke Xu
(Tsinghua University, China; 360 Vulnerability Research Institute, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p839-p (type: Full Paper) doi:10.1145/3832783.3837471

	Supplementary Material: Supplementary material for Evidence-Grounded Logic Vulnerability Detection for Smart Contracts via Runtime Context Reasoning
	RcAudit implementation for "Evidence-Grounded Logic Vulnerability Detection for Smart Contracts via Runtime Context Reasoning" (doi:10.5281/zenodo.19345906): The implementation of RcAudit tool.

Fully Automating Template Polyhedral Analysis by Leveraging LLMs
Renjie Huang, Liqian Chen, Hongfei Fu, Banghu Yin, Dengping Wei, and Ji Wang
(National University of Defense Technology, China; Shanghai University of Finance and Economics, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p849-p (type: Full Paper) doi:10.1145/3832783.3837472

	Poster: Fully Automating Template Polyhedral Analysis by Leveraging LLMs: This poster summarizes our novel program analysis approach that synergistically integrates LLMs with the template polyhedra domain. It presents the workflow and experimental results on several real-world programs.
	Reproduction Package for "Fully Automating Template Polyhedral Analysis by Leveraging LLMs" (doi:10.5281/zenodo.19245386): Please read and refer to the content at https://doi.org/10.5281/zenodo.19245386.

When Does AI Actually Help in Incident Response? Identifying Good First Messages in Cloud Service Incidents
Minghua Ma, Rujia Wang, Chetan Bansal, Saravan Rajmohan, Yingnong Dang, and Hongyu Zhang
(Microsoft, USA; Chongqing University, China)

Publisher's Version Article: ase26main-p860-p (type: Full Paper) doi:10.1145/3832783.3837473

We Must Have Missed This Comment: Detecting and Repairing Stale Function References in Linux Kernel Comments
Kexin Sun, Yunbo Lyu, Xutong Ma, Hongyu Kuang, Ratnadira Widyasari, He Zhang, Xiaoxing Ma, Julia Lawall, and David Lo
(Nanjing University, China; Singapore Management University, Singapore; Inria, France)

Publisher's Version Article: ase26main-p908-p (type: Full Paper) doi:10.1145/3832783.3837474

LARA: Static ReDoS Detection for Regular Expressions with Lookahead via Matching Automata
Mengxi Wang, Chengyao Peng, Weihao Su, Guiyi He, Rongchen Li, Hong Huang, and Haiming Chen
(Institute of Software at Chinese Academy of Sciences, China; University of Chinese Academy of Sciences, China)

Publisher's Version Article: ase26main-p997-p (type: Full Paper) doi:10.1145/3832783.3837475

ConfFuzz: Parameter-Aware Greybox Fuzzing for Configurable Cloud Systems
Shuai Wang, Hao Wang, Darko Marinov, Tianyin Xu, and Yongle Zhang
(University of Illinois at Urbana-Champaign, USA; University of California at Berkeley, USA; Purdue University, USA)

Publisher's Version Article: ase26main-p1001-p (type: Full Paper) doi:10.1145/3832783.3837476

Synthesizing File-Level Data for Unit Test Generation with Chain-of-Thoughts via Self-Debugging
Ziyue Hua, Tianyu Chen, Yeyun Gong, Shuai Lu, Peng Cheng, Qinglin Zhu, Yibo He, Yingjie Fu, Wenpin Jiao, Wei Yang, and Tao Xie
(Peking University, China; Microsoft Research, China; King's College London, UK; Fudan University, China)

Publisher's Version Article: ase26main-p1002-p (type: Full Paper) doi:10.1145/3832783.3837477

FAiLGen: Calibrating LLM for Failing Test Generation with Monte Carlo Tree Search
Tsz-On Li, Xiaochuan Yan, Dehui Yi, Yuhang Jiang, Kexin Li, Congying Xu, Ying Wang, and Shing-Chi Cheung
(Hong Kong University of Science and Technology, Hong Kong; Guangzhou HKUST Fok Ying Tung Research Institute, China; Northeastern University, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p1022-p (type: Full Paper) doi:10.1145/3832783.3837478

	Presentation video of the paper: Presentation video of FAiLGen: Calibrating LLM for Failing Test Generation with Monte Carlo Tree Search
	Reproduction package for "FAiLGen: Calibrating LLM for Failing Test Generation with Monte Carlo Tree Search" (doi:10.5281/zenodo.21765663): Code and experimental data of FAiLGen.

Feature-Focused Test Generation
José Antonio Zamudio Amaya, Gaetano Sapia, Alexi Turcotte, David Benavides, Marcel Böhme, and Andreas Zeller
(CISPA Helmholtz Center for Information Security, Germany; MPI-SP, Germany; Universidad de Sevilla, Spain)

Publisher's Version Article: ase26main-p1023-p (type: Full Paper) doi:10.1145/3832783.3837479

SecChain: Operationalizing Security Guidelines for Multi-agent Smart Contract Generation
Dianxiang Sun, Liming Nie, and Yang Liu
(Nanyang Technological University, Singapore; Shenzhen Technology University, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p1030-p (type: Full Paper) doi:10.1145/3832783.3837480

SecChain: Source Code and Replication Package (doi:10.5281/zenodo.21784541): Archival replication package for the ASE 2026 paper SecChain: Operationalizing Security Guidelines for Multi-agent Smart Contract Generation. The package includes the implementation, dataset-selection and knowledge-base snapshot manifests, local reconstruction tooling, reproduction scripts, a helper for fetching the ...

SafeDep: Detecting State Mutation Unsoundness in Rust via Dependency Slicing and LLM Reasoning
Zihao Rao, Yilin Chen, Chengjun Chen, and Hui Xu
(Fudan University, China; Ant Group, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p1035-p (type: Full Paper) doi:10.1145/3832783.3837481

Reproduction Package for "SafeDep: Detecting State Mutation Unsoundness in Rust via Dependency Slicing and LLM Reasoning" (doi:10.5281/zenodo.21695976): This artifact contains the source code of SafeDep, scripts for reproducing the experiments, benchmark programs, and experimental results reported in the paper. It provides the necessary materials to reproduce the evaluation of SafeDep for detecting unsound state mutations in Rust.

A Selective Undo/Redo Algorithm for Dependency-Constrained Operation Histories Based on Change Propagation
Xiaoxiong Fan, Hou Tam, Hanxi Zhu, and Song-Hai Zhang
(Tsinghua University, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p1098-p (type: Full Paper) doi:10.1145/3832783.3837482

A Selective Undo/Redo Algorithm for Dependency-Constrained Operation Histories Based on Change Propagation (Artifact) (doi:10.5281/zenodo.21788289): Artifact accompanying the ASE 2026 paper “A Selective Undo/Redo Algorithm for Dependency-Constrained Operation Histories Based on Change Propagation.” The artifact contains archived metric logs and fuzzing logs from the evaluation campaign, scripts for differential correctness validation, scripts for regenerating the ...

WiDepFuzz: Finding Wi-Fi Protocol Bugs in Mobile Hotspot via Field Dependency Model
Yuanliang Chen, Fuchen Ma, Taotao Gu, and Yu Jiang
(Renmin University of China, China; Tsinghua University, China)

Publisher's Version Article: ase26main-p1165-p (type: Full Paper) doi:10.1145/3832783.3837483

CTForge: Automatically Generating Test Suites for Software Configuration
Yuanliang Zhang, Zhizheng Zheng, Shanshan Li, Zhouyang Jia, Chaopeng Luo, Liqian Chen, Zhenbang Chen, Ji Wang, and Xiangke Liao
(National University of Defense Technology, China)

Publisher's Version Article: ase26main-p1197-p (type: Full Paper) doi:10.1145/3832783.3837484

Panorama: Unveiling Latent Dependencies for Microservice Autoscaling via Meta-learning
Zhuangbin Chen, Hongjiang Feng, Yang Liu, Juzheng Zheng, Xiaoyu He, and Zibin Zheng
(Sun Yat-sen University, China)

Publisher's Version Article: ase26main-p1217-p (type: Full Paper) doi:10.1145/3832783.3837485

Panorama: Unveiling Latent Dependencies for Microservice Autoscaling via Meta-learning - Poster: Poster used for presentation at the ASE 2026, presenting Panorama’s latent dependency mining, dependency-aware prediction, and rapid adaptation for Kubernetes autoscaling.

ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories
Ali Reza Ibrahimzada, Brandon Paulsen, Daniel Kroening, and Reyhaneh Jabbarvand
(University of Illinois at Urbana-Champaign, USA; Amazon, USA)

Publisher's Version Published Artifact Artifacts Available Artifacts Functional Article: ase26main-p1257-p (type: Full Paper) doi:10.1145/3832783.3837486

Reproduction Package for Article "ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories" (doi:10.5281/zenodo.21842351): Reproduction Package for Article "ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories". It includes code and necessary data to run the tool end-to-end.

Aligning User Requirement with Large Language Model in Code Generation
Jia Li, Ruiqi Bai, Yangkang Luo, Yiran Zhang, Wentao Yang, Zeyu Sun, Tiankuo Zhao, Dongming Jin, Lei Li, and Zhi Jin
(Wuhan University, China; Nanyang Technological University, Singapore; Institute of Software at Chinese Academy of Sciences, China; Peking University, China; University of Hong Kong, Hong Kong)

Publisher's Version Article: ase26main-p1298-p (type: Full Paper) doi:10.1145/3832783.3837487

QDoctor: Probe-Based Testing for Quantum Programs
Qichen Wang, Shangzhou Xia, Xiaoyu Guo, and Jianjun Zhao
(Kyushu University, Japan)

Publisher's Version Article: ase26main-p1302-p (type: Full Paper) doi:10.1145/3832783.3837488

Doc2Feat-Bench: Evaluating Documentation-Driven Feature Addition
Zhonghao Jiang, Le Deng, Jialun Cao, Michael Pradel, and Zhongxin Liu
(Zhejiang University, China; Hong Kong University of Science and Technology, Hong Kong; CISPA Helmholtz Center for Information Security, Germany)

Publisher's Version Article: ase26main-p1306-p (type: Full Paper) doi:10.1145/3832783.3837489

RegoMender: A Multi-agent Framework for Automated Rego Policy Repair
Ruijie Zhang, Huaxiao Yin, Li Hu, Fanqi Kong, Haozhe Liang, Shaoyin Cheng, Kun Zhang, and Bibo Tu
(Institute of Information Engineering at Chinese Academy of Sciences, China; University of Chinese Academy of Sciences, China; University of Science and Technology of China, China; Peking University, China; Anhui Province Key Laboratory of Digital Security, China)

Publisher's Version Article: ase26main-p1325-p (type: Full Paper) doi:10.1145/3832783.3837490

	Paper Slide: Slides used for the opening presentation at ASE '26
	Poster: PaperPoster for ASE' 26

Defensive Capability Analysis for JavaScript Libraries
Wenyuan Xu and Anders Møller
(Aarhus University, Denmark)

Publisher's Version Published Artifact Artifacts Available Artifacts Reusable Article: ase26main-p1332-p (type: Full Paper) doi:10.1145/3832783.3837491

Reproduction Package for "Defensive Capability Analysis for JavaScript Libraries" (doi:10.5281/zenodo.21840178): This artifact implements the paper's AST-based and selective points-to-based capability analyses for JavaScript and TypeScript libraries, together with a protected runtime that rejects dangerous access patterns. It contains the implementation source code, a Docker-based execution environment, pinned benchmark ...

RAVEN: Measuring Detection Instability in Anti-virus Engines under Semantics-Preserving Perturbations
Younghoon Ban, Beomjin Jin, Doowon Kim, Hyoungshick Kim, and Haehyun Cho
(Soongsil University, Republic of Korea; Ajou University, Republic of Korea; University of Tennessee, Knoxville, USA; Sungkyunkwan University, Republic of Korea)

Publisher's Version Article: ase26main-p1356-p (type: Full Paper) doi:10.1145/3832783.3837492

CiL-Agent: Compiler-in-the-Loop LLM Agent for Memory-Safe C Program Repair
Yang Shen, Yating Zhang, Jiaqiang Yao, Minghao Liu, and Wei Dong
(National University of Defense Technology, China)

Publisher's Version Article: ase26main-p1378-p (type: Full Paper) doi:10.1145/3832783.3837493

poster of CiL-Agent(ase26main-p1378-p): This is a promotional poster based on the core work of the CiL-Agent paper (ase26main-p1378-p).

Safe Multi-site Binary Instrumentation of Running x86-64 Programs
Jihun Baek, Sanghoon Han, and Hyungon Moon
(UNIST, Republic of Korea)

Publisher's Version Article: ase26main-p1407-p (type: Full Paper) doi:10.1145/3832783.3837494

Mobile Bug Reproduction via Global State Reprioritization and LLM-Guided Trajectory Exploration
Dingbang Wang, Sidong Feng, William G. J. Halfond, and Tingting Yu
(University of Connecticut, USA; Chinese University of Hong Kong, China; University of Southern California, USA)

Publisher's Version Article: ase26main-p1450-p (type: Full Paper) doi:10.1145/3832783.3837495

IncSFS: Incremental Full-Sparse Flow-Sensitive Pointer Analysis for C/C++
Kunlin Liu, Zhenbang Chen, Piyi Zu, Yide Du, and Ji Wang
(National University of Defense Technology, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p1456-p (type: Full Paper) doi:10.1145/3832783.3837496

Reproduction Package for Article "IncSFS: Incremental Full-Sparse Flow-Sensitive Pointer Analysis for C/C++" (doi:10.5281/zenodo.21771594): This artifact accompanies **“IncSFS: Incremental Full-Sparse Flow-Sensitive Pointer Analysis for C/C++.”** It packages the implementation, six subject programs, version-pair datasets, raw logs, structured results, and scripts used to inspect or reproduce the paper's evaluation. The artifact is distributed through ...

ExcavatorFuzz: LLM-Guided Path-Difficulty-Driven Directed Greybox Fuzzing
Kaiyu Xie, Siyuan Li, Jiaqian Peng, Yun Yang, Yaowen Zheng, Kai Cheng, Jiayu Zhang, Shizhao Tian, Yubo Li, and Hongsong Zhu
(Institute of Information Engineering at Chinese Academy of Sciences, Beijing, China; Shandong University, China)

Publisher's Version Article: ase26main-p1484-p (type: Full Paper) doi:10.1145/3832783.3837497

GANADI: Uncovering C/C++ OSS Reuse Genealogies via Pivotal Function-Based Clustering to Enhance Supply Chain Security
Dongyeon Kim, Seunghoon Woo, and Heejo Lee
(Korea University, Republic of Korea)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p1485-p (type: Full Paper) doi:10.1145/3832783.3837498

Artifact for “GANADI: Uncovering C/C++ OSS Reuse Genealogies via Pivotal Function-Based Clustering to Enhance Supply Chain Security” (doi:10.5281/zenodo.21768585): This artifact provides the GANADI source code, selected data, configuration files, and derived experimental outputs. GANADI consists of three main stages: OSS collection, pivotal function-based clustering, and reuse genealogy graph construction. The artifact supports the execution of the GANADI pipeline and the ...

OrthCoder: Balancing Security and Utility in Secure Code Generation via Orthogonal Adaptation
Menghan Tian, Youliang Yuan, Zhiqing Zhong, and Pinjia He
(Chinese University of Hong Kong, Shenzhen, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p1510-p (type: Full Paper) doi:10.1145/3832783.3837499

OrthCoder: Balancing Security and Utility in Secure Code Generation via Orthogonal Adaptation (doi:10.5281/zenodo.19336463): The data and scripts of OrthCoder

Zero-Knowledge VMs: Security and Usability in Practice
Jinan Jiang, Jinzhao Chu, Pengyu Xue, Xinghao Peng, Haoran Qin, and Xiapu Luo
(Hong Kong Polytechnic University, Hong Kong)

Publisher's Version Article: ase26main-p1549-p (type: Full Paper) doi:10.1145/3832783.3837500

Formal Verification-Integrated Reinforcement Learning for Automated ORM Schema Synthesis
Md Rashedul Hasan and Hamid Bagheri
(University of Nebraska-Lincoln, USA)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p1565-p (type: Full Paper) doi:10.1145/3832783.3837501

	ReinforceORM Presentation Slide Deck: Presentation slide deck highlighting problem domain, approach summary, key contributions, evaluation results , key takeaways, and impact of this work.
	Formal Verification-Integrated Reinforcement Learning for Automated ORM Schema Synthesis (Poster): This artifact is the conference poster for the ASE 2026 paper “Formal Verification-Integrated Reinforcement Learning for Automated ORM Schema Synthesis.” It summarizes ReinforceORM, a framework that casts ORM schema synthesis as multi-objective reinforcement learning with Alloy-based formal verification to balance ...
	ReinforceORM Presentation Video: This video summarizes the entire contribution and discusses the merit, objectives, impact and key takeaways of our work.
	One Slide Presentation: A One Slide presentation highlighting problem domain, approach summary, key contributions, evaluation results and impact of this work.
	Formal Verification-Integrated Reinforcement Learning for Automated ORM Schema Synthesis (doi:10.6084/m9.figshare.30071260.v10): This artifact package contains the complete materials needed to evaluate ReinforceORM for ASE 2026 under Available, Functional, and Reusable badges. It includes: (1) executable software (`components/`, `reproduction/`, `Minimal_Example_CLI_Tool/`), (2) curated datasets and frozen experiment states (`Dataset/`, ...

Repository-Aware Metamorphic Relation Generation for Augmented Reality Applications using Large Language Models
Dibyendu Brinto Bose, Jiawei Qin, and Chris Brown
(Virginia Tech, USA)

Publisher's Version Article: ase26main-p1578-p (type: Full Paper) doi:10.1145/3832783.3837502

Learning to Triage Vulnerability Reports from Program Analysis: An Empirical Study in Node.js
Ronghao Ni, Aidan Z.H. Yang, Min-Chien Hsu, Nuno Sabino, Limin Jia, Ruben Martins, Darion Cassel, and Kevin Cheang
(Carnegie Mellon University, USA; Athanor AI, USA; University of California at Berkeley, USA)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p1614-p (type: Full Paper) doi:10.1145/3832783.3837503

Learning to Triage Vulnerability Reports from Program Analysis: An Empirical Study in Node.js (Artifact) (doi:10.5281/zenodo.21846194): TRIAGE-JS accompanies our empirical study of learning-based approaches for triaging vulnerability reports produced by the NodeMedic-FINE program-analysis tool. The artifact provides the training and evaluation pipeline used in the study, covering classical machine-learning models, graph neural networks, fine-tuned and ...

Code Transformation Rule Synthesis using LLMs: Potential and Limits
Axel Allain, Aymeric Blot, Djamel Eddine Khelladi, and Mathieu Acher
(INSA, France; University of Rennes, France; Inria, France; CNRS, France; IRISA, France)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p1631-p (type: Full Paper) doi:10.1145/3832783.3837504

Experiment results (doi:10.6084/m9.figshare.31861126.v1): Experiment data with rule generation for each dataset/DSL/model. The data are used for computing evaluation metrics and figures.

A Low-Cost Human-in-the-Loop Investigation of Toxicity on GitHub at Scale
Rahat Rizvi Rahman, Mia Mohammad Imran, and Kostadin Damevski
(Virginia Commonwealth University, USA; Missouri University of Science and Technology, USA)

Publisher's Version Article: ase26main-p1633-p (type: Full Paper) doi:10.1145/3832783.3837505

Generation of Web Apps with Agentic IDEs: An Empirical Assessment
Manuel Marceca, Maria Teresa Rossi, and Leonardo Mariani
(University of Milano-Bicocca, Italy; Gran Sasso Science Institute, Italy)

Publisher's Version Article: ase26main-p1651-p (type: Full Paper) doi:10.1145/3832783.3837506

Looks Good, but Does It Run? A Large-Scale Empirical Study of the Executability of Example Code in Model Cards
Simeng Yao, Jialin Zhao, Yang Zhang, Tun Li, Tao Wang, Changrong Xie, Zezhou Tang, and Yiwen Wu
(National University of Defense Technology, China)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p1672-p (type: Full Paper) doi:10.1145/3832783.3837507

Replication Package for Article 'Looks Good, but Does It Run? A Large-Scale Empirical Study of the Executability of Example Code in Model Cards' (doi:10.5281/zenodo.21339847): The artifact provides the data, code, and results supporting replication of our study’s executability analysis, error classification, repair-strategy analysis, and automated repair experiments on example code in Hugging Face model cards.

From Thread to Pool: Modeling and Static Detection of Thread Pool Misuses in Java Programs
Baoquan Cui, Yucheng Qiu, Rui Han, Hang Gao, and Jian Zhang
(Institute of Software at Chinese Academy of Sciences, Beijing, China; Hangzhou Institute for Advanced Study at University of Chinese Academy of Sciences, Hangzhou, China; University of Chinese Academy of Sciences, China)

Publisher's Version Article: ase26main-p1687-p (type: Full Paper) doi:10.1145/3832783.3837508

HERO: Hypothesis-Centered Root-Cause Analysis for Microservice Incidents
Jiewei Lyu, Junquan Yi, Shu Liang, Pengfei Chen, and Long Pan
(Sun Yat-sen University, China; Tencent, China)

Publisher's Version Article: ase26main-p1707-p (type: Full Paper) doi:10.1145/3832783.3837509

Gray-Box Fuzzing in Local Space
Martin Jonáš, Jan Strejček, and Marek Trtík
(Masaryk University, Czech Republic)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p1719-p (type: Full Paper) doi:10.1145/3832783.3837510

CPS evaluation artifact (doi:10.5281/zenodo.21797253): The results from the evaluation of the approach "Gray-box fuzzing in local space" and scripts used for processing raw data. The artifact comprises both binaries and source code of our tools and binaries of state-of-the-art tools (for performance comparison). If you are interested only in actual results (and scripts ...

Revisiting LLMs on New Feature Implementation in Real-World Software Development Practices
Jia Li, Tingxuan Huang, Tiankuo Zhao, Yiming Wang, Yiran Zhang, Anshun Hu, Kechi Zhang, Lecheng Wang, Zinan Sheng, Kui Liu, Ge Li, and Zhi Jin
(Wuhan University, China; Nanyang Technological University, Singapore; Peking University, China; Huawei Technologies, China)

Publisher's Version Article: ase26main-p1768-p (type: Full Paper) doi:10.1145/3832783.3837511

Self-Discovering Security Oracles: Meta-learning Vulnerability Detection Strategies through Adversarial Self-Play
Md Rashedul Hasan and Hamid Bagheri
(University of Nebraska-Lincoln, USA)

Publisher's Version Published Artifact Artifacts Available Article: ase26main-p1822-p (type: Full Paper) doi:10.1145/3832783.3837512

	MetaMorphSES Presentation Slide Deck: Presentation slide deck highlighting problem domain, approach summary, key contributions, evaluation results , key takeaways, and impact of this work.
	Self-Discovering Security Oracles: Meta-learning Vulnerability Detection Strategies through Adversarial Self-Play (Poster): This artifact is the conference poster for the ASE 2026 paper “Self-Discovering Security Oracles: Meta-learning Vulnerability Detection Strategies through Adversarial Self-Play” by Md Rashedul Hasan and Hamid Bagheri (University of Nebraska–Lincoln). The poster presents MetaMorphSES: generator and detector agents that ...
	MetaMorphSES Presentation Video: This video summarizes the entire contribution and discusses the merit, objectives, impact and key takeaways of our work.
	One Slide Presentation: A One Slide presentation highlighting problem domain, approach summary, key contributions, evaluation results and impact of this work.
	Self-Discovering Security Oracles: Meta-learning Vulnerability Detection Strategies through Adversarial Self-Play (doi:10.6084/m9.figshare.30505922.v8): Executable, reproducible artifact package for the ASE 2026 paper on MetaMorphSES: adversarial meta-learning for vulnerability detection and generation (self-discovering security oracles). The package provides implementation code (Red/Blue Team, security oracle), evaluation datasets (CVEfixes/Draper slices and ...

S2CAgent: A Self-Learning Agent Knowledge Graph Framework for Software Supply Chain Analysis
Youfei Huang, Zhong Li, Minxue Pan, and Xuandong Li
(Nanjing University, China)

Publisher's Version Article: ase26main-p1823-p (type: Full Paper) doi:10.1145/3832783.3837513

ArkEval: Benchmarking and Evaluating Automated Code Repair for ArkTS
Bang Xie, Senjian Zhang, Zhiyuan Peng, Wei Chen, Xin Yin, Chenhao Ying, and Yuan Luo
(Shanghai Jiao Tong University, China; Zhejiang University, China)

Publisher's Version Article: ase26main-p1862-p (type: Full Paper) doi:10.1145/3832783.3837514

From Vibe to Spec: An Empirical Study to Demystify Specifications in Code Generation
Ruirui He, Hanqing Lu, Lezhi Ma, Kai Ye, Qiong Wu, Shangqing Liu, Lei Bu, and Xuandong Li
(Nanjing University, China)

Publisher's Version Article: ase26main-p1876-p (type: Full Paper) doi:10.1145/3832783.3837515

Instruction Alignment for Binary Code Representation Learning
Huaijin Wang and Shuai Wang
(Shandong University, China; Hong Kong University of Science and Technology, Hong Kong)

Publisher's Version Published Artifact Artifacts Available Artifacts Functional Article: ase26main-p1967-p (type: Full Paper) doi:10.1145/3832783.3837516

Reproduction Package for Article "Instruction Alignment for Binary Code Representation Learning" (doi:10.5281/zenodo.21696749): InsnAlign builds instruction-level embeddings on top of binary-function encoders (jTrans and CLAP) and uses them to (1) recover source-level correspondences between functions compiled with different compilers / optimization levels, and (2) synergize function-level retrieval with instruction-level alignment scores (MAS ...

Formula Completion Suggestions for Alloy Models with Selection Guidance
Mohammad Nurullah Patwary and Allison Sullivan
(University of Texas at Arlington, USA)

Publisher's Version Article: ase26main-p1981-p (type: Full Paper) doi:10.1145/3832783.3837517

COBug: A Bug Localization Pipeline for COBOL: Does It Work? An Exploratory Study
Kavyasri Gajula, Phanindra Kodela, and Sridhar Chimalakonda
(Indian Institute of Technology Tirupati, India)

Publisher's Version Article: ase26main-p1990-p (type: Full Paper) doi:10.1145/3832783.3837518