
Higher-Scoring Coding Models Did Not Get More Work Done Yining Hua arxiv.org/abs/2611.23216 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

New Software Engineering papers from arxiv.org: design tools, software metrics. Thank you to arXiv for use of its open access interoperability.

Higher-Scoring Coding Models Did Not Get More Work Done Yining Hua arxiv.org/abs/2611.23216 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

Identifying and Repairing Energy Smells with Agent Skills Mohammadjavad Mehditabar, Saurabhsingh Rajput, Tushar Sharma arxiv.org/abs/2611.23203 [𝚌𝚜.𝚂𝙴]

stable-envs-v1: Fast and Reproducible Environments with Controllable Variations Sami BuGhanem, Francesco Capuano, Ahitagni Das, Richard Gao, Randall Balestriero arxiv.org/abs/2611.23151 [𝚌𝚜.𝚂𝙴]

Mind the Gap: A Deployed Multi-Agent System for Documentation Maintenance Lorenzo Masoero arxiv.org/abs/2611.23142 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝙻] 💬Accepted at IAAI-27 (Innovative Applications of AI, co-located with AAAI 2027), Emerging Applications track

BugGen 2.0: Rethinking the Roles of LLMs for Scalable RTL Bug Synthesis Minh Luu, Michael Quinn, Aakash Tyagi, David Houngninou, Jiang Hu arxiv.org/abs/2611.23091 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]

Think Before You Code: A Benchmark for Testing LLMs on Software Engineering Deliberation Ashman Mehra arxiv.org/abs/2611.22905 [𝚌𝚜.𝚂𝙴]

Missing Security-Fix Backporting for GitHub Actions Workflows Chengyan Ma, Jieke Shi, Ruidong Han, Weifeng Sun, Yuqing Niu, Yunbo Lyu, … arxiv.org/abs/2611.22519 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙲𝚁] 💬Accepted by the 49th IEEE/ACM International Conference on Software Engineering (ICSE 2027)

Adaptive Budget Allocation for Smart-Contract Fuzzing: Why Online Feedback Fails to Improve Vulnerability Triage Yanzi Liu, Jiachi Tong arxiv.org/abs/2611.22430 [𝚌𝚜.𝚂𝙴] 💬Accepted to the 22nd International Conference on Mobility, Sensing and Networking (MSN 2026)

BehaVerify: A Formal Verification Tool for Behavior Trees Serena S. Serbinowska, Ben Wooding, Diego Manzanas Lopez, Luke Nam, Anne M. Tumlin, Nicholas K. Potteiger, Hongchao Zhang, Taylor T. Johnson arxiv.org/abs/2611.22403 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙻𝙾 𝚌𝚜.𝚁𝙾]

Formal Analysis of a Fault-Tolerant Extension of the ROSACE Flight Controller Marco Bozzano, Alessandro Cimatti, Moussa Fall, Stefano Tonetta arxiv.org/abs/2611.22394 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝚂𝙲]

Agent Trajectories as Evidence for Software Quality Assurance Jonathan Ullrich, Julien Siebert, Michael Kläs, Adam Trendowicz, Andreas Jedlitschka arxiv.org/abs/2611.22323 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸] 💬Submitted to ICSE2027 AMPLIFY Workshop conf.researchr.org/home/icse…

Operating an Agent-Driven Dataset Factory: Discovery, Construction, and Public Release Eduardo Ariño de la Rubia, Szilard Pafka arxiv.org/abs/2611.21957 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙼𝙰] 💬Code: github.com/earino/factory-pr…

EmbedGym: Letting Coding Agents Develop and Debug Embedded Firmware Without Physical Hardware Minghui Zhao, Yiming Li, Sophie Zhu, Maxwell Khor, Lauren Ouyang, Hai "Helen" Li, Yiran Chen, Tingjun Chen arxiv.org/abs/2611.21845 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]

Can Coding Agents Write and Transpile Unit Tests Gil Pasternak, AJ Langley, Tom Yotam, Ellie Kitanidis arxiv.org/abs/2611.21797 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]

Revisiting the Survival of Agent-Attributed Code: How Measurement Choices Decide the Verdict Musfiqur Rahman, Mahi Begoug, Emad Shihab arxiv.org/abs/2611.21784 [𝚌𝚜.𝚂𝙴 𝚌𝚜.𝙰𝙸]

Beyond Leaderboard Ranks: Selecting Software Engineering Agents Under Budget Constraints Srinath Srinivasan, Tim Menzies arxiv.org/abs/2611.21515 [𝚌𝚜.𝚂𝙴]