{"slug": "study-coding-agents-rarely-retrieve-open-source-contribution-rules", "title": "Study: Coding agents rarely retrieve open-source contribution rules", "summary": "A study by researchers evaluating four frontier coding agents found that the agents almost never proactively retrieve open-source contribution rules, despite 106 curated issues from 49 repositories containing such rules. The agents improved disclosure and verification with reminders and feedback, but never refused to contribute in AI-banned repositories under any tested condition, indicating that enforcing bans and human escalations remains an open problem.", "body_md": "# Computer Science > Software Engineering\n\n[Submitted on 29 Jul 2026]\n\n# Title:A First Look at Coding Agents' Compliance with AI Contribution Rules in Open-Source Communities\n\n[View PDF](/pdf/2607.26819)\n\n[HTML (experimental)](https://arxiv.org/html/2607.26819v1)\n\nAbstract:Open source communities have been flooded with AI-generated contributions. In defense, they have written contribution rules to regulate coding agents' behavior, spanning from a total ban, mandatory disclosure, to verification gates and human sign-offs. Yet, whether coding agents read and follow those rules, and behave in open source repositories, remains unknown. To estimate real-world rule compliance of coding agents, we curate 106 issues from 49 repositories containing AI contribution rules into RepoComplianceBench. We judge the trajectory of each run against the repository's rules, measuring whether the agent refuses to contribute, discloses its assistance truthfully, clears the required verification gates, or escalates critical steps to a human. We also test if extra prompts, rule disclosure, or feedback from the compliance verifier help with the situation. Our experiments on four frontier models show that today's agents almost never proactively retrieve the contribution rules. Agents pick up disclosure and verification with reminder prompts, rule quotes, and verifier feedback; however, they never refuse to contribute in AI-banned repositories under any condition we tested. The status reveals that verification and disclosure issues are solvable with existing mechanisms, yet enforcing bans and human escalations remains an open problem.\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/study-coding-agents-rarely-retrieve-open-source-contribution-rules", "canonical_source": "https://arxiv.org/abs/2607.26819", "published_at": "2026-07-31 12:28:22+00:00", "updated_at": "2026-07-31 12:53:18.761035+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-policy", "ai-ethics"], "entities": ["RepoComplianceBench"], "alternates": {"html": "https://wpnews.pro/news/study-coding-agents-rarely-retrieve-open-source-contribution-rules", "markdown": "https://wpnews.pro/news/study-coding-agents-rarely-retrieve-open-source-contribution-rules.md", "text": "https://wpnews.pro/news/study-coding-agents-rarely-retrieve-open-source-contribution-rules.txt", "jsonld": "https://wpnews.pro/news/study-coding-agents-rarely-retrieve-open-source-contribution-rules.jsonld"}}