[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-ai-proves-its-own-math-and-uses-it-to-prove-more-math":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},2878,"ai-proves-its-own-math-and-uses-it-to-prove-more-math","AI Proves Its Own Math and Uses It to Prove More Math","A new pipeline called CPL has LLMs generating mathematical conjectures and verifying proofs in Lean 4, then feeding their own verified work back as context.","An AI research pipeline is now generating novel mathematical theorems, proving them formally, and using those proofs to get better at proving the next ones.\n\nResearchers introduced a system called the Conjecturing-Proving Loop, or CPL, which runs inside Lean 4, a formal proof assistant where every logical step is machine-checked. The loop works in two alternating phases: an LLM proposes a mathematical conjecture, then attempts to prove it. If the proof checks out, that theorem-proof pair gets added to the model's context for the next iteration. No extra training, no fine-tuning — just the model reading its own verified track record before trying again.\n\nThe self-referential trick is what makes this worth paying attention to. Most neural theorem-proving systems generate statements and proofs in a single pass; CPL splits them, letting proof difficulty inform what gets conjectured next. The researchers found this separation meaningfully increases the discovery rate of theorems that are hard to prove — the ones that actually matter to mathematicians. The fact that a model's own formally verified outputs make it measurably better at subsequent tasks is a concrete data point for in-context learning doing real work, not just pattern-matching.\n\nFor context: formal verification has long been the gap between \"the AI got the right answer\" and \"the AI can be trusted.\" Lean 4 closes that gap by rejecting any proof with a logical flaw. That CPL operates inside this constraint, rather than just generating plausible-looking math, puts it in different territory than most headline-grabbing AI-solves-math stories — though the gap between automated conjecture generation and Fields Medal-level insight remains considerable.","[\"ai\",\"math\",\"formal-verification\",\"research\"]","2026-06-30T04:00:00.000Z","2026-06-30T14:27:11.668Z","2026-06-30T14:27:14.571Z","published",null,[],"ai",[24,26,27,28],"math","formal-verification","research",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.14274",0,{"sections":35},[36,40,45,50,55,60,65,70,75,80,85,89,94,99],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":44},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":46,"slug":47,"count":48,"latest_published_at":49},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Dev Tools","dev-tools",59,"2026-07-07T04:00:00.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":86,"slug":87,"count":83,"latest_published_at":88},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":95,"slug":96,"count":97,"latest_published_at":98},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]