iiinova — where your digital self keeps evolving

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Roxane Koitz-Hristov, Franz Wotawa: Choosing an energy-efficient software architecture for building system diagnostic support arxiv.org/abs/2610.06444 arxiv.org/pdf/2610.06444 arxiv.org/html/2610.06444

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Paul Darius Mandl, Peter Mandl, Martin H\"ausl: LLM Non-Determinism in Deterministic Processes: A Controlled Variation Space for Constraining the Propagation of Non-Determinism arxiv.org/abs/2610.06255 arxiv.org/pdf/2610.06255 arxiv.org/html/2610.06255

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Hai Dang Truong, Rayner Goh, Thanh Le-Cong, Yintong Huo: Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents arxiv.org/abs/2610.06193 arxiv.org/pdf/2610.06193 arxiv.org/html/2610.06193

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Taha Rostami, Jeongju Sohn, Mike Papadakis: Where Does the Budget Go? Structural Concentration in Learning-Based Mutant Selection arxiv.org/abs/2610.06055 arxiv.org/pdf/2610.06055 arxiv.org/html/2610.06055

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Larissa Salerno, Haoyu Gao, Gregory Gay, Alexander Serebrenik, Philipp Leitner: Let the Agent Do It? How Software Practitioners Understand and Make Permission Decisions in Agentic AI Assistants arxiv.org/abs/2610.06047 arxiv.org/pdf/2610.06047 arxiv.org/html/2610.06047

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Elizabeth Bjarnason, Johan Lin{\aa}ker, Fabian Fagerholm: Experimentation Practices in Indie Game Startups arxiv.org/abs/2610.06004 arxiv.org/pdf/2610.06004 arxiv.org/html/2610.06004

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Christoph B\"uhler, Matteo Biagiola, Luca Di Grazia, Guido Salvaneschi: AgentSpy: Making AI Agent Behavior Observable arxiv.org/abs/2610.06001 arxiv.org/pdf/2610.06001 arxiv.org/html/2610.06001

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Peter Fettke, Wolfgang Reisig: From Trust-by-Design to Continuous Trust in the Era of Artificial Intelligence arxiv.org/abs/2610.05991 arxiv.org/pdf/2610.05991 arxiv.org/html/2610.05991

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Wei Wu: Mechanizing the User's Eye: Pre-Registered Deployment of a Sabotage-Validated Fail-Plausible Observer in a Production LLM Agent Runtime arxiv.org/abs/2610.05981 arxiv.org/pdf/2610.05981 arxiv.org/html/2610.05981

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Muhammad Usman, Johan Lin{\aa}ker, Deepika Badampudi, Hannes Salin: Adopting InnerSource in a Public Sector Organization: A Case Study arxiv.org/abs/2610.05947 arxiv.org/pdf/2610.05947 arxiv.org/html/2610.05947

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Taiki Wakamatsu, Yuta Ishimoto, Masanari Kondo, Yasutaka Kamei: PreMaQ: Predicting Maintainability-Related Quality of LLM-Generated Code Before Generation arxiv.org/abs/2610.05858 arxiv.org/pdf/2610.05858 arxiv.org/html/2610.05858

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Ankit Kumar, Thirumoorthi Thangamani: Finite State Machine-Based Traffic Orchestration for Multi-Engine Analysis Platforms arxiv.org/abs/2610.05788 arxiv.org/pdf/2610.05788 arxiv.org/html/2610.05788

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Dolly Sah, Tanmay Sah, Harshul Jain, Tanya Sah: UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents arxiv.org/abs/2610.05622 arxiv.org/pdf/2610.05622 arxiv.org/html/2610.05622

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Jingzhi Gong, Jie M. Zhang, Gunel Jahangirova, Meng Wang: Adaptive Code Revision Attacks on AI Pull Request Reviewers arxiv.org/abs/2610.05399 arxiv.org/pdf/2610.05399 arxiv.org/html/2610.05399

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Tingxuan Tang (Luna), Zilong Chen (Luna), Yue (Luna), Xiao: Understanding the Hierarchical Structure and Functional Landscape of the Model Context Protocol Ecosystem arxiv.org/abs/2610.05319 arxiv.org/pdf/2610.05319 arxiv.org/html/2610.05319

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Jian Gu, Hongyu Zhang, Chunyang Chen, Aldeida Aleti: Mind the Gaps: From Failure Attribution to Closed-Form Repair of Code Language Models arxiv.org/abs/2610.05277 arxiv.org/pdf/2610.05277 arxiv.org/html/2610.05277

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Yongyuan Peng, Zhou Feng, Tongying Wu, Jiahao Chen, Yuan Su, Chunyi Zhou, Tianyu Du, Shouling Ji: StateWise: Diagnosing and Repairing Persistent Operational State Before Agent Actions arxiv.org/abs/2610.05241 arxiv.org/pdf/2610.05241 arxiv.org/html/2610.05241

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Lezhi Ma, Han Wang, Shangqing Liu, Jiawan Wang, Lei Bu: SpecAgent: Empowering Program Verification with Agentic Synthesis of Formal Program Specifications arxiv.org/abs/2610.05132 arxiv.org/pdf/2610.05132 arxiv.org/html/2610.05132

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Ruida Hu, Yuanhao Wang, Chao Peng, Yakun Zhang, Cuiyun Gao: Beyond Task Completion: Measuring Interaction Cost in Terminal User Interfaces arxiv.org/abs/2610.05047 arxiv.org/pdf/2610.05047 arxiv.org/html/2610.05047

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Yu Ji, Yang Wei, Yutao Hu, Haojun Zhao, Yueming Wu, Deqing Zou: Characterizing Security Effects of OSS Vulnerabilities in Agent Systems arxiv.org/abs/2610.05036 arxiv.org/pdf/2610.05036 arxiv.org/html/2610.05036

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Luo, Gao, Zhou, Liu, You, Sun, Zhang, Fu, Wang, Pei: Rethinking Tool Design for Agentic RCA: A Controlled Empirical Study arxiv.org/abs/2610.05009 arxiv.org/pdf/2610.05009 arxiv.org/html/2610.05009

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Yunhao Liang, Chengguang Gan, Ruixuan Ying, Hanjun Wei, Zhe Cui, Shiwen Ni: LLM-Based Test Generation: Information Sources, Generation Strategies, and Quality Evidence arxiv.org/abs/2610.05001 arxiv.org/pdf/2610.05001 arxiv.org/html/2610.05001

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Yujia Luo, Haonan Zhang, Jiasi Shen, Zishuo Ding, Weiyi Shang: TeleGen: Improving LLM-Based Web Application Generation via Runtime Telemetry arxiv.org/abs/2610.04981 arxiv.org/pdf/2610.04981 arxiv.org/html/2610.04981

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Bihui Jin, Yinxi Li, Kaiyuan Wang, Pengyu Nie: Assembling Insights for Agentic Machine Learning Engineering Systems arxiv.org/abs/2610.04927 arxiv.org/pdf/2610.04927 arxiv.org/html/2610.04927

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Yifan Xiong, Jingyi Ge, Zhenpeng Chen, Yiling Lou: Complex Agents, Shallow Tests: Demystifying and Enhancing Test Adequacy of Agent Harness in the Wild arxiv.org/abs/2610.04921 arxiv.org/pdf/2610.04921 arxiv.org/html/2610.04921

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Jiajie Wang, Yutong Zhao, Kebin Peng, Sen He, Qing Guo, Tianlin Li: CARET: Training-Free Test-Time Scaling for Repository-Level Code Completion arxiv.org/abs/2610.04837 arxiv.org/pdf/2610.04837 arxiv.org/html/2610.04837

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Jiajie Wang, Yutong Zhao, Tianlin Li, Huashan Chen, Jinfu Chen, Kebin Peng, Sen He: Agent Skill Evolution: How Revisions Affect Coding Agents arxiv.org/abs/2610.04832 arxiv.org/pdf/2610.04832 arxiv.org/html/2610.04832

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Arjun Subramanian, George Xu, Nithilan Karthik: Asymmetric Repository Lineage Modeling and Verifier-Guided Coordination in Concurrent AI Coding Agents arxiv.org/abs/2610.04779 arxiv.org/pdf/2610.04779 arxiv.org/html/2610.04779

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

He Yang Yuan, Haonan Zhang, Xin Wang, An Ran Chen, Kisub Kim, Zishuo Ding, Zhenhao Li: Towards Automatically Pruning Logging Code with Coding Agents: How Far Are We? arxiv.org/abs/2610.04716 arxiv.org/pdf/2610.04716 arxiv.org/html/2610.04716

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Rabeya Khatun Muna, Muhammad Ahasanuzzaman, Nakhla Rafi, Yisen Xu, Jinqiu Yang, Tse-Hsun Chen: RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair arxiv.org/abs/2610.04658 arxiv.org/pdf/2610.04658 arxiv.org/html/2610.04658

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Tairan Wang, Earl T. Barr: Back to the Future: Regressing Readability Features from LLMs arxiv.org/abs/2610.04641 arxiv.org/pdf/2610.04641 arxiv.org/html/2610.04641

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Xiang Li, Aichun Huang, Mingming Zhang, Zheli Liu: When Talk Isn't Code: Comparing LLM Agents That Simulate and Develop Software arxiv.org/abs/2610.04639 arxiv.org/pdf/2610.04639 arxiv.org/html/2610.04639

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Fran\c{c}ois Hublet, David Basin, Sr{\dj}an Krsti\'c: Practical Runtime Enforcement of First-Order Temporal Requirements arxiv.org/abs/2610.04611 arxiv.org/pdf/2610.04611 arxiv.org/html/2610.04611

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Qinghua Xu, Guancheng Wang, Boxi Yu, Liting Lin, Lionel Briand: DreamTest: World-Model Surrogates for Search-Based Testing of Deep Reinforcement Learning Agents arxiv.org/abs/2610.04494 arxiv.org/pdf/2610.04494 arxiv.org/html/2610.04494

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Yuechen Li, Yige Yang, Tao Yue: Noise-Resilient Testing of Quantum Programs Based on Output Dominance arxiv.org/abs/2610.04461 arxiv.org/pdf/2610.04461 arxiv.org/html/2610.04461

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

He, Li, Jin, Zhang, Li, Li, Huang, Zhan, Wen, Jiao: World Requirement Model: Learning Requirement-Change Consequences from Typed Artifact Graphs arxiv.org/abs/2610.04445 arxiv.org/pdf/2610.04445 arxiv.org/html/2610.04445

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Huiyun Peng, Ricardo Calvo, Kelechi G. Kalu, James C. Davis: How Do Coding Agents Optimize Software and Report Performance Validation? A Large-Scale Empirical Study of Open-Source Pull Requests arxiv.org/abs/2610.03969 arxiv.org/pdf/2610.03969 arxiv.org/html/2610.03969

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Henrique Mandelli Canella, Yohan Duarte, Cristiano Politowski, Vinicius Durelli, Andre Takeshi Endo: Characterizing Open-Source Video Games from a Software Engineering Perspective arxiv.org/abs/2610.03953 arxiv.org/pdf/2610.03953 arxiv.org/html/2610.03953

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

Ornela Danushi, Flavio Sampirisi, Jacopo Soldani, Stefano Forti, Antonio Brogi: Smells and Refactorings for Software Environmental Sustainability: A Systematic Literature Review arxiv.org/abs/2610.03838 arxiv.org/pdf/2610.03838 arxiv.org/html/2610.03838

010

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 16h

[2026-10-06 Tue (UTC), 39 new articles found for csSE Software Engineering]

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 05/10/2026

Takeharu Mitsui: Pinning Decisions Before Failure: Executable Records of Underspecified Choices in AI-Assisted Code Generation arxiv.org/abs/2610.03237 arxiv.org/pdf/2610.03237 arxiv.org/html/2610.03237

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 05/10/2026

Siyu Wang, Yifan Wang, Yuecheng He: MintEval: Do LLMs Implement the Trading Strategy You Asked For? A Behavioural-Equivalence Benchmark for Natural-Language-to-Strategy Code arxiv.org/abs/2610.03080 arxiv.org/pdf/2610.03080 arxiv.org/html/2610.03080

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 05/10/2026

Astekin, Tun, Goknil, Husom, Shar, S\"ozer, Widyasari, Song: Engineering Sustainable Agents: A Systematic Comparison of Agentic LLMs for Developer Workflows arxiv.org/abs/2610.03010 arxiv.org/pdf/2610.03010 arxiv.org/html/2610.03010

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 05/10/2026

Mingyan Gao, Celine W\"ust, Zuming Jiang, Zhendong Su: BISCEPTER: Probability-Driven Bisection for Large-Scale System Software arxiv.org/abs/2610.02995 arxiv.org/pdf/2610.02995 arxiv.org/html/2610.02995

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 05/10/2026

Masahiro Kato: GTDD: Generative Test-Driven Development for AI Coding Agents with Adversarial Testing arxiv.org/abs/2610.02952 arxiv.org/pdf/2610.02952 arxiv.org/html/2610.02952

010

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 05/10/2026

Xin Xu, Siru Tao: Discriminating Fixture Coverage in Agent-Infrastructure Verification Suites arxiv.org/abs/2610.02928 arxiv.org/pdf/2610.02928 arxiv.org/html/2610.02928

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 05/10/2026

Naing Oo Lwin: VeriPy Source-Preserving Verification and Compatibility Checking for Python Components arxiv.org/abs/2610.02814 arxiv.org/pdf/2610.02814 arxiv.org/html/2610.02814

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 05/10/2026

Li, Shi, Li, Yang, Wang, Wang, Huang, Yu, Liu, Mi, Liang: Self-Supervised Scaling of Terminal Environments for Scientific Domains arxiv.org/abs/2610.02710 arxiv.org/pdf/2610.02710 arxiv.org/html/2610.02710

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 05/10/2026

Yun-Yun Tsai, Yuning Mao, Shiqi Wang, Junfeng Yang, Sinong Wang: WebUIProof: Benchmarking WebUI Code Generators with UI-Agent Execution Harness arxiv.org/abs/2610.02617 arxiv.org/pdf/2610.02617 arxiv.org/html/2610.02617

000

arXiv cs.SE Software Engineering @csse-bot.bsky.social · 05/10/2026

Rekhi, Zhang, Islam, Pasham, Chitturi, Paramesha, Valiveti, Imran, Turkkan, Kosar: Improving the Energy-Efficiency of the Code Generated by LLMs through Effective Prompting arxiv.org/abs/2610.02571 arxiv.org/pdf/2610.02571 arxiv.org/html/2610.02571

000