[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-llm-generated-plans-now-come-with-formal-proofs":10,"sections":34},{"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":29,"feedback":33,"feedback_at":22,"cost_usd":33,"total_tokens":33},7535,"llm-generated-plans-now-come-with-formal-proofs","LLM Generated Plans Now Come With Formal Proofs","A new system has an LLM write general planning programs and mathematically prove they solve every case, not just the test cases.","An AI system can now prove, not just claim, that its plans actually work every time.\n\nResearchers built a pipeline that uses an LLM, GPT-5.6-Sol, to generate \"generalized plans\" - programs meant to solve every instance of a planning problem, like packing boxes or routing blocks. The twist: the system also converts the planning domain's rules from PDDL into Lean, a formal proof language, and has the same LLM write a mathematical proof that the plan works for every valid instance. Lean's own kernel checks the proof, so there's no room for a persuasive-but-wrong argument to slip through. Across 13 standard benchmark domains, the approach produced a plan with a verified completeness proof for 12 of them.\n\nThis matters because prior LLM-based planning work could only claim success by running a pile of test cases and hoping nothing broke outside that sample. That's the same weak spot that undermines trust in a lot of AI-generated code: it looks right until it isn't. Swapping \"passed our tests\" for \"proven correct by a theorem checker\" is a real jump in what these systems can promise, especially for domains like logistics or robotics where an edge-case failure isn't just annoying, it's expensive.\n\nOne domain still resisted proof, a reminder that formal verification of AI-written plans is progress, not a solved problem, and Lean expertise remains a niche skill standing between this result and anyone actually using it.","[\"ai\",\"formal-verification\",\"planning\",\"llm\"]","2026-09-24T04:00:00.000Z","2026-09-24T05:01:36.402Z","2026-09-24T05:01:42.784Z","published",null,[],"ai",[24,26,27,28],"formal-verification","planning","llm",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.27105",0,{"sections":35},[36,39,43,48,53,58,63,68,73,78,83,88,93,98],{"name":37,"slug":24,"count":38,"latest_published_at":18},"AI",4387,{"name":40,"slug":41,"count":42,"latest_published_at":18},"Security","security",720,{"name":44,"slug":45,"count":46,"latest_published_at":47},"Policy","policy",380,"2026-09-23T22:53:43.000Z",{"name":49,"slug":50,"count":51,"latest_published_at":52},"Deals","deals",220,"2026-09-23T22:00:00.000Z",{"name":54,"slug":55,"count":56,"latest_published_at":57},"Hardware","hardware",173,"2026-09-23T23:42:10.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":62},"Science","science",135,"2026-09-23T22:45:49.000Z",{"name":64,"slug":65,"count":66,"latest_published_at":67},"Consumer Tech","consumer-tech",116,"2026-09-24T00:51:49.000Z",{"name":69,"slug":70,"count":71,"latest_published_at":72},"Software","software",85,"2026-09-23T20:00:00.000Z",{"name":74,"slug":75,"count":76,"latest_published_at":77},"Dev Tools","dev-tools",79,"2026-09-22T22:21:13.000Z",{"name":79,"slug":80,"count":81,"latest_published_at":82},"Startups","startups",66,"2026-09-23T17:28:38.000Z",{"name":84,"slug":85,"count":86,"latest_published_at":87},"Gaming","gaming",45,"2026-09-22T15:35:06.000Z",{"name":89,"slug":90,"count":91,"latest_published_at":92},"General","general",43,"2026-09-21T23:48:56.000Z",{"name":94,"slug":95,"count":96,"latest_published_at":97},"Reviews","reviews",27,"2026-09-22T13:00:00.000Z",{"name":99,"slug":100,"count":101,"latest_published_at":102},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]