arXiv cs.SE Software Engineering

Sebastian Pandolfi, Guzm\'an Llamb\'ias, Laura Gonz\'alez: An EVM-Cosmos Bridge for Atomic, Semantic-Preserving Transfer of Environmental Tokens https://arxiv.org/abs/2610.37663 https://arxiv.org/pdf/2610.37663 https://arxiv.org/html/2610.37663

Yunlong Wang, Alyssa Wu, Cuiyun Gao, Jia Feng, Songyuanyi Lu, Zhichao Hu: FeatureArc: Benchmarking Coding Agents on Evolving Features https://arxiv.org/abs/2610.37434 https://arxiv.org/pdf/2610.37434 https://arxiv.org/html/2610.37434

Tianrong Zhang, Yakun Zhang, Dan Hao: HIDE: Hierarchical Isolation via Documentation and Evidence for Rustc Bugs https://arxiv.org/abs/2610.37343 https://arxiv.org/pdf/2610.37343 https://arxiv.org/html/2610.37343

Nicolas Tacheny, Tom Mens, Sa\"id Mahmoudi: Mind the Intent Gap: A Methodology for Collaborative Agent-Driven Software Engineering https://arxiv.org/abs/2610.37340 https://arxiv.org/pdf/2610.37340 https://arxiv.org/html/2610.37340

Felipe de Sant'Anna Paix\~ao, Dhyego Tavares, Eduardo Almeida, Iftekhar Ahmed: Hidden in Plain Sight: an Empirical Study about The Instruction Stacks of Coding Agents https://arxiv.org/abs/2610.37332 https://arxiv.org/pdf/2610.37332 https://arxiv.org/html/2610.37332

Islem Bouzenia, Michael Pradel: BenchMeUp: Building Software Engineering Benchmarks from Natural-Language Specifications https://arxiv.org/abs/2610.37283 https://arxiv.org/pdf/2610.37283 https://arxiv.org/html/2610.37283

Jiahong Xiang, Kunqiu Chen, Lingming Zhang, Yuqun Zhang: Spine: Compiling Subtask Trees into Structured Context for Long-Horizon Coding Agents https://arxiv.org/abs/2610.37224 https://arxiv.org/pdf/2610.37224 https://arxiv.org/html/2610.37224

Andriy Miranskyy, Jose Campos: Toward Circuit-Aware Mutation Testing for Quantum Programs: Exact Visibility and Execution Planning https://arxiv.org/abs/2610.36976 https://arxiv.org/pdf/2610.36976 https://arxiv.org/html/2610.36976

Andie Huang, Ying Pang, Qian Zhang, Yihang Cheng, Lin Ma: Does More Thinking Pay Off? Reasoning Cost and Correctness of LLMs in Code Generation and Bug Fixing https://arxiv.org/abs/2610.36952 https://arxiv.org/pdf/2610.36952 https://arxiv.org/html/2610.36952

S M Abdulla Al Mamun, Akif Islam, Mohd. Ruhul Ameen: Beyond QASecClaw: Agent Scaling, Verifier Feedback, and Evidence Reliability in Software Assurance https://arxiv.org/abs/2610.36947 https://arxiv.org/pdf/2610.36947 https://arxiv.org/html/2610.36947

Chen Liu, Bernhard Vogginger, Christian Mayr: A lightweight C Code Generator for Heterogeneous TinyML Systems https://arxiv.org/abs/2610.36907 https://arxiv.org/pdf/2610.36907 https://arxiv.org/html/2610.36907

Wang, Jin, Li, Jin, Tian, Fang, Ye, Zhao: ASNER: Software Architecture Recovery with Adaptive Semantic Neighborhoods and Evidence-Grounded Refinement https://arxiv.org/abs/2610.36894 https://arxiv.org/pdf/2610.36894 https://arxiv.org/html/2610.36894

Kazi Amit Hasan, Enrong Pan, Yuan Tian, Mariam Guizani, Steven H. H. Ding: A Fine-Grained Empirical Study of Upstream Security Events and Downstream Mitigation in Maven https://arxiv.org/abs/2610.36603 https://arxiv.org/pdf/2610.36603 https://arxiv.org/html/2610.36603

Binhang Qi, Yiming Liu, Yun Lin, Yangjie Zhou, Hailong Sun, Jin Song Dong: Benchmarking LLM Agents for Behaviorally Adequate Test Generation from Software Requirements https://arxiv.org/abs/2610.36584 https://arxiv.org/pdf/2610.36584 https://arxiv.org/html/2610.36584

Jiameng Bai, Zhitao Wang, Long Wang, Keyue Qian, Sai Wu: From Ripple to Boundary: Deterministic Impact Boundaries for LLM-Based Software Evolution https://arxiv.org/abs/2610.36549 https://arxiv.org/pdf/2610.36549 https://arxiv.org/html/2610.36549

Zexin Li, Weibo Zhang, Linyi Li, Arvind Easwaran, Simin Chen: ProCerDCL: Query-Efficient Black-Box Probabilistic Verification of Deep Learning Compiler Optimization https://arxiv.org/abs/2610.36499 https://arxiv.org/pdf/2610.36499 https://arxiv.org/html/2610.36499

Ali Shakiba: When AI Can Build It, What Should We Assess? Rethinking Evidence of Engineering Competence https://arxiv.org/abs/2610.36413 https://arxiv.org/pdf/2610.36413 https://arxiv.org/html/2610.36413

Haocong Jiang, Sadra Sabouri, Sepand Haghighi, Souti Chattopadhyay: Your Wish Is My Commit: Over-Compliant Refactoring in AI Coding Agents https://arxiv.org/abs/2610.36346 https://arxiv.org/pdf/2610.36346 https://arxiv.org/html/2610.36346

Wenxin Jiang, Mikola Lysenko: Instant Software Factories https://arxiv.org/abs/2610.36254 https://arxiv.org/pdf/2610.36254 https://arxiv.org/html/2610.36254

Horikawa, Li, Kashiwa, Ouatiti, Sayagh, Adams, Iida, Hassan: Agent or Human? Detecting Commits by AI Coding Agents in the Absence of Authorship Signatures https://arxiv.org/abs/2610.36229 https://arxiv.org/pdf/2610.36229 https://arxiv.org/html/2610.36229

Zihan Fang, Ron Asoulin-Handelman, Helen Wu, Yu Huang, Gina R. Bai: Can AI Guide Testing Without Generating Tests? A Comparative Study of AI-Assisted Unit Testing https://arxiv.org/abs/2610.36185 https://arxiv.org/pdf/2610.36185 https://arxiv.org/html/2610.36185

Yuvraj Sehgal, Mahsa Panahandeh, Naser Ezzati-Jivan: Stratum: Repository Memory for Coding Agents Beyond the Context Window https://arxiv.org/abs/2610.36153 https://arxiv.org/pdf/2610.36153 https://arxiv.org/html/2610.36153

Yuvraj Sehgal, Mahsa Panahandeh, Naser Ezzati-Jivan: Context Is a Pipeline, Not a Window: Information Attrition in LLM Agent Harnesses https://arxiv.org/abs/2610.36114 https://arxiv.org/pdf/2610.36114 https://arxiv.org/html/2610.36114

Maghera, Arya, Babikian, Chechik, Dehnavi: AGDecode: Semantic Attribute Grammar Derivatives for Safety-Constrained Decoding of Large Language Models https://arxiv.org/abs/2610.36105 https://arxiv.org/pdf/2610.36105 https://arxiv.org/html/2610.36105

Daxerer, Glock, Macho, Ramler, Pinzger, Pichler: Do Coding Agents Still Need a Debugger? Frontier-Model-Based Fault Localization at the Accuracy Ceiling https://arxiv.org/abs/2610.36015 https://arxiv.org/pdf/2610.36015 https://arxiv.org/html/2610.36015

Xinyuan Song, Hasibul Haque, Jay Somasundaram, Ryan Turner, Bowen Zhu, Liang Zhao: CIVER: Causal Intervention Verification for Reliable Code Review https://arxiv.org/abs/2610.36010 https://arxiv.org/pdf/2610.36010 https://arxiv.org/html/2610.36010

Thupakula Sai Varun: Before the First Edit? Measuring When Coding-Agent Guidance Actually Arrives https://arxiv.org/abs/2610.35992 https://arxiv.org/pdf/2610.35992 https://arxiv.org/html/2610.35992

Marco Paina, Mark Niklas M\"uller, Niels M\"undler-Sasahara, Martin Vechev: PROBE: Frontier Coding Agents Find Different Bugs Than Maintainers Fix https://arxiv.org/abs/2610.35987 https://arxiv.org/pdf/2610.35987 https://arxiv.org/html/2610.35987

Zinovyeva, Taleb, Kozodoi, Schleicher, Namazi, Kraus, Kent, Jensen: Generation and Verification: Human-Agent Collaboration for Safety-Critical Automotive Software Engineering https://arxiv.org/abs/2610.35982 https://arxiv.org/pdf/2610.35982 https://arxiv.org/html/2610.35982

Alexander Kovalenko, Artem Redchych: Small agents should know what their tools do https://arxiv.org/abs/2610.35981 https://arxiv.org/pdf/2610.35981 https://arxiv.org/html/2610.35981

Yijun Zhou, et al.: UnityBench-Mini3D: Evaluating LLM Agents for 3D Game Development in Unity https://arxiv.org/abs/2610.35980 https://arxiv.org/pdf/2610.35980 https://arxiv.org/html/2610.35980

Zhongjie Wang, Xiang He, Xiao Wang, Mingyi Liu, Shuang Yu, Hanchuan Xu: Testing Agentic Service Systems: An Agentic Living Lab Methodology Across the Physical-Digital Continuum https://arxiv.org/abs/2610.35978 https://arxiv.org/pdf/2610.35978 https://arxiv.org/html/2610.35978

Srinath Srinivasan, Lunxiao Li, Tim Menzies, Wesley Assun\c{c}\~ao: Continue or Restart? The Limits of Early Failure Prediction in Coding Agents https://arxiv.org/abs/2610.35971 https://arxiv.org/pdf/2610.35971 https://arxiv.org/html/2610.35971

[2026-10-28 Wed (UTC), 33 new articles found for csSE Software Engineering]

Jiangnan Huang, Bin Lin, Yutaro Kashiwa: FLOWSTEP: A Framework for Learning to Predict GitHub Actions Workflow STEPs https://arxiv.org/abs/2610.35650 https://arxiv.org/pdf/2610.35650 https://arxiv.org/html/2610.35650

Rongkang Li, Jiaxin Hu, Taolue Chen, Yong Li, Fu Song, Zhilin Wu: Ranking Function Generation with LLMs for Termination https://arxiv.org/abs/2610.35523 https://arxiv.org/pdf/2610.35523 https://arxiv.org/html/2610.35523

Fernando Vallecillos-Ruiz, Islem Bouzenia, Michael Pradel, Leon Moonen: The Hidden Costs of Forgetting: A Study of Trajectory Deletion in Software Engineering Agents https://arxiv.org/abs/2610.35496 https://arxiv.org/pdf/2610.35496 https://arxiv.org/html/2610.35496

Jia Feng, Alyssa Wu, Cuiyun Gao, Yunlong Wang, Songyuanyi Lu, Zhichao Hu: FeatureLoop: Benchmarking Coding Agents under Evolving Requirements https://arxiv.org/abs/2610.35488 https://arxiv.org/pdf/2610.35488 https://arxiv.org/html/2610.35488

Qingyun Yang, Zejun Zhang, Dapeng Yan, Tian Zhang, Zhenchang Xing, Yi Li, Zhiming Liu: Understanding Python Linters through a Comprehensive and Systematic Empirical Study https://arxiv.org/abs/2610.35485 https://arxiv.org/pdf/2610.35485 https://arxiv.org/html/2610.35485

Mostafijur Rahman Akhond, Mahmuda Khatun, Gias Uddin: Making Small Code LLMs More Efficient for Secure Code Review with Neuro-Symbolic Fine-Tuning https://arxiv.org/abs/2610.35477 https://arxiv.org/pdf/2610.35477 https://arxiv.org/html/2610.35477

Sebastian Baltes, Christoph Treude: Toward Evidence-Based Agentic Software Engineering https://arxiv.org/abs/2610.35348 https://arxiv.org/pdf/2610.35348 https://arxiv.org/html/2610.35348

Huanyu Liu, Yezheng Cheng, Jinliang You, Tianxiao Huang, Linyu Li, Zheng Fang, Peng Cao, Ge Li: RepoTrace: Improving Requirement Tracing in Multi-Round Agent Interactions https://arxiv.org/abs/2610.35333 https://arxiv.org/pdf/2610.35333 https://arxiv.org/html/2610.35333

Milanese, Salzano, Muradyan, Wu, Pareschi, Fasano, Fazzini: Testing with Coding Agents: A Large-Scale Comparison of Agent-Supported and Human-Authored Pull Requests https://arxiv.org/abs/2610.35297 https://arxiv.org/pdf/2610.35297 https://arxiv.org/html/2610.35297

Yongxiang Hu, Ruiyang Liu, Qining He, Xuan Wang, Yangfan Zhou: Chart the Invisible: Interactive Perception for Hidden-Target Exploration in GUI Agents https://arxiv.org/abs/2610.35237 https://arxiv.org/pdf/2610.35237 https://arxiv.org/html/2610.35237

Yiwen Fu, Binhang Qi, Xiao Li, Runlin Liu, Hailong Sun, Xiang Gao: Behavioral Regression Detection for Pull Requests via Structured Oracles https://arxiv.org/abs/2610.35223 https://arxiv.org/pdf/2610.35223 https://arxiv.org/html/2610.35223

Feng, Xiong, Zeng, Chen, Guan, Wang, Tao, Xue, Dong: V$^3$AST-Bench: Verifiable, Valid, and Versatile Safety Evaluation for Coding Agents https://arxiv.org/abs/2610.35188 https://arxiv.org/pdf/2610.35188 https://arxiv.org/html/2610.35188

Assaf Marron, David Harel: Toward Methods and Tools for Critical Examination of Disparate Systems for Discovery of Hidden Dependencies in Engineering of Autonomous and Semi-Autonomous Systems https://arxiv.org/abs/2610.34974 https://arxiv.org/pdf/2610.34974 https://arxiv.org/html/2610.34974

Ruwei Pan, Linhao Wu, Yakun Zhang, Zixiong Yang, Lu Zhang, Hongyu Zhang: Rivet: Utility-Preserving Context Control for Repository-Level Coding Agents https://arxiv.org/abs/2610.34967 https://arxiv.org/pdf/2610.34967 https://arxiv.org/html/2610.34967

Zhe Yin, Yuling Shi, Xiaodong Gu, Beijun Shen: Reasoning Patterns for Efficient AI Coding: An Empirical Study https://arxiv.org/abs/2610.34943 https://arxiv.org/pdf/2610.34943 https://arxiv.org/html/2610.34943

Christoph Treude, Sebastian Baltes: How Do Coding-Agent Harnesses Self-Evolve? An Empirical Study of Retrospective Adaptation https://arxiv.org/abs/2610.34938 https://arxiv.org/pdf/2610.34938 https://arxiv.org/html/2610.34938