[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-llm-based-tool-beats-standard-methods-at-finding-cps-bugs":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},6920,"llm-based-tool-beats-standard-methods-at-finding-cps-bugs","LLM-Based Tool Beats Standard Methods at Finding CPS Bugs","A new tool uses LLMs to hunt for spec-breaking bugs in cyber-physical systems, beating standard search methods on most benchmark tests.","A new tool turns large language models into bug-hunters for the software that runs machinery, cars, and robots.\n\nResearchers built LLM-Falsifier, a system that searches for cases where a cyber-physical system violates its formal specification, written in a math notation called Signal Temporal Logic. Instead of using traditional numerical search algorithms, it prompts an LLM repeatedly, feeding it not just numbers but natural-language variable names, full output trajectories, and the exact moments where the system came closest to failing. Tested on the ARCH-COMP benchmark suite, a standard proving ground for this kind of tool, it needed fewer simulation runs than existing methods on 14 of 21 specifications.\n\nFalsification tools have long relied on purpose-built optimizers: Bayesian search, surrogate models, search-based testing. The fact that a general-purpose LLM, handed extra context a numerical solver would ignore, can out-search several of those specialized tools suggests the advantage isn't raw computation but interpretation - the model appears to reason about what the trajectory data means, not just crunch it.\n\nStill, it lost on 7 of the 21 specifications, and the paper measures success in simulations needed, not wall-clock time or dollars - an LLM call is far slower and pricier per query than a Bayesian optimizer, so \"more sample-efficient\" isn't the same as \"cheaper\" yet.","[\"ai\",\"formal-verification\",\"cyber-physical-systems\",\"testing\"]","2026-09-18T04:00:00.000Z","2026-09-18T22:43:39.169Z","2026-09-18T22:43:51.064Z","published",null,[],"ai",[24,26,27,28],"formal-verification","cyber-physical-systems","testing",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.20752",0,{"sections":35},[36,39,43,48,53,57,61,66,70,75,80,85,90,95],{"name":37,"slug":24,"count":38,"latest_published_at":18},"AI",4082,{"name":40,"slug":41,"count":42,"latest_published_at":18},"Security","security",661,{"name":44,"slug":45,"count":46,"latest_published_at":47},"Policy","policy",339,"2026-09-17T12:00:00.000Z",{"name":49,"slug":50,"count":51,"latest_published_at":52},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":54,"slug":55,"count":56,"latest_published_at":18},"Hardware","hardware",155,{"name":58,"slug":59,"count":60,"latest_published_at":18},"Science","science",125,{"name":62,"slug":63,"count":64,"latest_published_at":65},"Consumer Tech","consumer-tech",99,"2026-09-09T17:27:33.000Z",{"name":67,"slug":68,"count":69,"latest_published_at":18},"Dev Tools","dev-tools",78,{"name":71,"slug":72,"count":73,"latest_published_at":74},"Software","software",75,"2026-09-10T20:41:21.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Startups","startups",55,"2026-09-09T23:14:29.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Gaming","gaming",43,"2026-09-10T12:18:06.000Z",{"name":86,"slug":87,"count":88,"latest_published_at":89},"General","general",41,"2026-09-08T01:57:23.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]