[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-ai-agents-get-a-tool-picker-that-notices-when-tools-break":10,"sections":35},{"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":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},11299,"ai-agents-get-a-tool-picker-that-notices-when-tools-break","AI Agents Get a Tool Picker That Notices When Tools Break","A new retrieval framework ranks AI agent tools by live reliability, not just semantic fit, cutting failed calls from 86% to 3% in outage tests.","An AI agent is only as good as the tools it can actually call - and a new framework tries to make sure it is calling the ones that work.\n\nResearchers describe RATED (Reliability-Aware Tool Retrieval via Execution Dynamics), a system that picks which external tools an AI agent should use. It pairs a frozen dual-encoder, fine-tuned for semantic matching, with a lightweight contextual bandit that re-ranks tool candidates using real-time execution feedback - meaning it learns which tools are currently failing and adjusts its picks without retraining the whole model. The team also built EcoAgent, a benchmark of 5,172 real-world tools and more than 210,000 query-tool pairs, to test retrieval accuracy and reliability together. On that benchmark, RATED posted a 52.2% relative improvement in retrieval accuracy (MRR) over the ToolLLM API retriever, and cut the rate of picking a broken tool from 86.2% to 2.9% during a simulated outage with a 30% failure rate - all while adding less than 1 millisecond of latency.\n\nMost tool-retrieval research treats availability as someone else's problem: find the semantically closest match and hope the API answers. That is a bad bet as agents increasingly chain together dozens of third-party tools with no uptime guarantees. Treating live failure data as a ranking signal, not an afterthought, is the more useful framing here, and the near-zero latency cost means it is not just a theoretical fix.\n\nStill, this is one team's benchmark, built and graded by the same people who built the retriever, so the 86-to-3 percent headline number deserves a skeptical read until someone runs it on a different fleet of tools.","[\"ai-agents\",\"tool-retrieval\",\"llm-benchmarks\",\"reliability\"]","2026-10-12T04:00:00.000Z","2026-10-12T06:46:18.826Z","2026-10-12T06:46:23.507Z","published",null,[],"ai",[26,27,28,29],"ai-agents","tool-retrieval","llm-benchmarks","reliability",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.13889",0,{"sections":36},[37,40,45,50,55,60,65,70,75,80,85,90,95,100],{"name":38,"slug":24,"count":39,"latest_published_at":18},"AI",6966,{"name":41,"slug":42,"count":43,"latest_published_at":44},"Security","security",952,"2026-10-12T04:54:12.000Z",{"name":46,"slug":47,"count":48,"latest_published_at":49},"Policy","policy",496,"2026-10-11T20:06:43.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Deals","deals",488,"2026-10-12T10:32:15.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",234,"2026-10-11T17:20:00.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Science","science",196,"2026-10-11T15:34:40.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Consumer Tech","consumer-tech",191,"2026-10-12T11:10:16.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Startups","startups",120,"2026-10-09T17:02:31.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Software","software",115,"2026-10-11T07:34:45.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Dev Tools","dev-tools",111,"2026-10-12T11:22:24.000Z",{"name":86,"slug":87,"count":88,"latest_published_at":89},"General","general",70,"2026-10-11T14:15:00.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"Gaming","gaming",59,"2026-10-09T11:43:43.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"Reviews","reviews",34,"2026-10-08T14:00:22.000Z",{"name":101,"slug":102,"count":103,"latest_published_at":104},"How-To","how-to",8,"2026-10-05T09:00:00.000Z"]