[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-when-ai-agents-use-science-tools-results-are-mixed":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},3192,"when-ai-agents-use-science-tools-results-are-mixed","When AI Agents Use Science Tools, Results Are Mixed","A new benchmark tests AI agents on geochemistry simulations and finds that tool access helps on average but quietly breaks things it used to get right.","Giving an AI agent access to a scientific simulator does not simply make it smarter — it also introduces new ways to fail.\n\nResearchers have released PHREEQC-MCQ-200, a 200-question benchmark that tests AI agents on aqueous-geochemistry simulations using PHREEQC, a widely used open-source chemistry modeling program. The benchmark requires agents to build simulator inputs, run the tool, read the outputs, and commit to a multiple-choice answer. Tested across several frontier and mid-tier model families, tool access raised average accuracy overall — but the improvement was not clean. Agents that gained points in some areas lost them in others, posting regressions that a single aggregate score would never reveal.\n\nThe finding matters because most evaluations of scientific AI stop at \"did accuracy go up?\" This benchmark surfaces something more useful: a tool-augmented agent can fail in ways a tool-free agent never would. A structured table-of-contents interface for reading simulator output, for example, cut token costs and helped stronger models — but hurt mid-tier models that could not reliably navigate it.\n\nThe broader point is that plugging an LLM into domain software is not a capability upgrade by itself; it is a new configuration with its own failure modes. As labs race to connect AI to lab instruments, simulation engines, and scientific databases, a benchmark that reports item-level retention and trajectory failures — not just a headline accuracy number — is exactly the kind of tool the field has been missing.","[\"ai\",\"benchmarks\",\"science\",\"dev-tools\"]","2026-07-02T04:00:00.000Z","2026-07-02T04:15:20.714Z","2026-07-02T04:15:23.744Z","published",null,[],"ai",[24,26,27,28],"benchmarks","science","dev-tools",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.00436",0,{"sections":35},[36,40,45,50,55,60,65,70,74,78,83,87,92,97],{"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":27,"count":72,"latest_published_at":73},"Science",66,"2026-07-10T10:29:37.000Z",{"name":75,"slug":28,"count":76,"latest_published_at":77},"Dev Tools",59,"2026-07-07T04:00:00.000Z",{"name":79,"slug":80,"count":81,"latest_published_at":82},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":84,"slug":85,"count":81,"latest_published_at":86},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":88,"slug":89,"count":90,"latest_published_at":91},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":93,"slug":94,"count":95,"latest_published_at":96},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":98,"slug":99,"count":100,"latest_published_at":101},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]