[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-a-new-benchmark-for-routing-queries-across-ai-agents":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},2634,"a-new-benchmark-for-routing-queries-across-ai-agents","A New Benchmark for Routing Queries Across AI Agents","Researchers built a 3,000-prompt test to measure how well systems pick the right AI agents for a job without wasting money on extras.","Picking the right AI agent for a task is harder than it sounds — and now there's a formal benchmark to measure it.\n\nResearchers published a benchmark derived from WildChat, a large dataset of real user conversations, containing 3,000 prompts mapped against a fixed catalog of 12 agents. The core problem they're testing is set-valued prediction: a single query might need one agent, or it might need three, and over-selecting runs up execution costs. Their evaluation protocol layers several metrics — Precision, Recall, F1, Jaccard, Exact Match — alongside latency and a cost-aware simulation that uses ordinal agent-cost tiers to score constrained routing decisions.\n\nThe findings matter because zero-shot LLM routing, the obvious default for anyone building a multi-agent system today, finishes near the bottom of the rankings. Supervised approaches — particularly a fine-tuned encoder — substantially outperform it on raw accuracy, while a simpler linear multilabel classifier holds up well as a practical baseline. Adding a weighted post-scoring layer called WAR on top of the encoder produced the best cost-constrained results.\n\nThis is the kind of unglamorous infrastructure work that determines whether multi-agent systems are actually useful or just expensive. Most coverage of AI agents focuses on capabilities; this focuses on dispatch, which is where real-world deployments quietly break down.","[\"ai\",\"multi-agent\",\"benchmarks\",\"research\"]","2026-06-30T04:00:00.000Z","2026-06-30T09:48:44.416Z","2026-06-30T09:48:47.391Z","published",null,[],"ai",[24,26,27,28],"multi-agent","benchmarks","research",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.28925",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"]