[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-new-method-keeps-ai-generated-code-commits-runnable":10,"sections":35},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},11012,"new-method-keeps-ai-generated-code-commits-runnable","New Method Keeps AI-Generated Code Commits Runnable","RucTangle splits messy AI-generated coding-agent patches into ordered, always-runnable commits that modestly boost bug-fixing by other agents.","AI coding agents make a mess when they commit code, and a new method called RucTangle cleans it up without breaking anything.\n\nResearchers built RucTangle, the first agentic tool to untangle large tangled patches from coding agents into separate, ordered commits that keep the code runnable at every step. They tested it against four existing untangling methods on 131 agent-generated patches. Where those baselines left 20.6% to 37.4% of commit histories unable to run, RucTangle's output ran every time. The team also built TangleEval, a framework to measure whether untangled histories actually help agents fix bugs, rather than just looking cleaner on paper.\n\nPrevious commit-untangling research only checked if split commits looked structurally similar to what a human would write, never whether they actually helped anyone. This study feeds 453 regression-causing patches to two other coding agents and measures real repair rates, finding a 5.2 percentage point bump in pass@1 when agents get RucTangle's cleaned-up history to work from.\n\nA 5.2 point bump is real, but modest. It says more about how little agent research has tested against actual software engineering practice than about RucTangle being a finished fix.","[\"coding agents\",\"commit untangling\",\"ai research\",\"software engineering\"]","2026-10-09T04:00:00.000Z","2026-10-10T01:57:45.271Z","2026-10-10T01:57:51.941Z","published",null,[],"ai",[26,27,28,29],"coding agents","commit untangling","ai research","software engineering",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.11593",0,{"sections":36},[37,40,44,49,54,58,62,67,72,77,81,86,91,96],{"name":38,"slug":24,"count":39,"latest_published_at":18},"AI",6733,{"name":41,"slug":42,"count":43,"latest_published_at":18},"Security","security",931,{"name":45,"slug":46,"count":47,"latest_published_at":48},"Policy","policy",486,"2026-10-08T22:40:11.000Z",{"name":50,"slug":51,"count":52,"latest_published_at":53},"Deals","deals",474,"2026-10-08T22:00:00.000Z",{"name":55,"slug":56,"count":57,"latest_published_at":18},"Hardware","hardware",232,{"name":59,"slug":60,"count":61,"latest_published_at":18},"Science","science",193,{"name":63,"slug":64,"count":65,"latest_published_at":66},"Consumer Tech","consumer-tech",181,"2026-10-08T23:26:35.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":71},"Startups","startups",117,"2026-10-08T16:45:00.000Z",{"name":73,"slug":74,"count":75,"latest_published_at":76},"Software","software",114,"2026-10-08T17:57:01.000Z",{"name":78,"slug":79,"count":80,"latest_published_at":18},"Dev Tools","dev-tools",106,{"name":82,"slug":83,"count":84,"latest_published_at":85},"General","general",66,"2026-10-09T04:46:11.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"Gaming","gaming",58,"2026-10-08T20:08:45.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Reviews","reviews",34,"2026-10-08T14:00:22.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"How-To","how-to",8,"2026-10-05T09:00:00.000Z"]