[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-researchers-find-llms-solve-optimization-problems-the-slow-way":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},9080,"researchers-find-llms-solve-optimization-problems-the-slow-way","Researchers Find LLMs Solve Optimization Problems the Slow Way","A new benchmark of 561 tasks finds most LLM-generated optimization code gets the right answer but runs slower than expert-written reference solutions.","A new benchmark shows large language models can write optimization code that gets the right answer and still runs painfully slow.\n\nResearchers built OptTips, a knowledge base of 50 expert modeling techniques across eight families, then used a multi-agent framework called OptDachshund to turn existing optimization benchmarks into paired tasks: one solved the standard way, one solved with expert techniques, both scored for correctness and solve time. The result is EfficientOpt, a set of 561 expert-reviewed tasks with reference solutions. Across 11 LLMs tested, the pattern held: when a model's code produced the correct objective value, it typically took longer to solve than the expert-built version of the same problem. Even narrowing to cases where the LLM's model used fewer variables and constraints than the reference, 57% still solved slower.\n\nThis matters because most LLM-for-math evaluations stop at did it get the right number. This benchmark shows that passing that bar can still leave you with code that is technically correct and practically expensive - slow to prepare data, slow to build the model, slow to solve, or some combination of the three. For anyone wiring LLMs into scheduling, routing, or resource-allocation systems where solve time is a real cost, correctness alone is not the metric that matters.\n\nGetting the right answer eventually is a low bar. Getting it before your cloud bill notices is the one that counts.","[\"llms\",\"optimization-modeling\",\"benchmarks\"]","2026-10-01T04:00:00.000Z","2026-10-01T18:55:05.888Z","2026-10-01T18:55:08.755Z","published",null,[],"ai",[26,27,28],"llms","optimization-modeling","benchmarks",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.38884",0,{"sections":35},[36,39,43,48,53,58,62,67,72,76,81,86,91,96],{"name":37,"slug":24,"count":38,"latest_published_at":18},"AI",5488,{"name":40,"slug":41,"count":42,"latest_published_at":18},"Security","security",809,{"name":44,"slug":45,"count":46,"latest_published_at":47},"Policy","policy",429,"2026-10-01T02:26:17.000Z",{"name":49,"slug":50,"count":51,"latest_published_at":52},"Deals","deals",298,"2026-09-30T21:00:26.000Z",{"name":54,"slug":55,"count":56,"latest_published_at":57},"Hardware","hardware",196,"2026-09-30T13:00:00.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":18},"Science","science",162,{"name":63,"slug":64,"count":65,"latest_published_at":66},"Consumer Tech","consumer-tech",149,"2026-09-30T22:57:11.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":71},"Dev Tools","dev-tools",93,"2026-10-01T02:30:48.000Z",{"name":73,"slug":74,"count":70,"latest_published_at":75},"Software","software","2026-09-30T21:41:11.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Startups","startups",84,"2026-09-30T20:39:09.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Gaming","gaming",51,"2026-09-30T16:24:30.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"General","general",50,"2026-09-30T21:37:54.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]