[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-longcats-ai-research-agent-ranks-second-rivals-unnamed":10,"sections":40},{"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":30,"tags":31,"sources":35,"feedback":39,"feedback_at":22,"cost_usd":39,"total_tokens":39},8458,"longcats-ai-research-agent-ranks-second-rivals-unnamed","LongCat's AI Research Agent Ranks Second, Rivals Unnamed","LongCat's multi-agent research system scored strong marks on three benchmarks and placed second of four in an undisclosed in-house test.","LongCat has published a technical report for an AI system that plans, researches, and writes full reports on its own.\n\nThe system, called LongCat-DeepResearch, splits the job into stages: planning agents scan outside sources and draft a plan the team calls a ResearchSpec, then separate research agents investigate and write their assigned sections in parallel, gathering their own evidence as they go. A global review step then flags specific sections for revision instead of rewriting the whole report from scratch. On three public report-quality benchmarks, DeepResearchBench, DeepResearchBench II, and ResearchRubrics, each scored on a scale that tops out near 100, it posted 55.25, 51.35, and 79.83. On an in-house benchmark it scored 76.04, good for second place among four systems tested.\n\nThat \"second of four\" ranking is the detail worth pausing on: LongCat's report never names the other three systems or their scores, so there is no way to tell whether it lost a close race or got beaten badly. The workflow itself, splitting planning from drafting, then editing only what needs it, is a sensible fix for the usual problem of AI-written reports collapsing into mush on revision. A self-reported rank with no visible competitors is not a comparison, it is a claim.\n\nFile this under wait-and-see until LongCat-DeepResearch runs against named competitors, in the open, on a benchmark where every score is on the table.","[\"ai\",\"deep-research\",\"benchmarks\",\"agents\"]","2026-09-30T04:00:00.000Z","2026-09-30T04:58:48.573Z","2026-09-30T04:58:54.343Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"Explain what DeepResearchBench, DeepResearchBench II, and ResearchRubrics actually measure (and their scale), and name the other systems in the four-way in-house comparison with their scores, since right now the piece cites five separate benchmark numbers without giving readers a way to judge whether they're good, bad, or how far behind the leader LongCat-DeepResearch really is.","resolved","ai",[30,32,33,34],"deep-research","benchmarks","agents",[36],{"name":37,"url":38},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.36071",0,{"sections":41},[42,45,49,53,58,63,68,73,78,83,88,93,98,103],{"name":43,"slug":30,"count":44,"latest_published_at":18},"AI",5028,{"name":46,"slug":47,"count":48,"latest_published_at":18},"Security","security",780,{"name":50,"slug":51,"count":52,"latest_published_at":18},"Policy","policy",417,{"name":54,"slug":55,"count":56,"latest_published_at":57},"Deals","deals",284,"2026-09-29T21:00:00.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":62},"Hardware","hardware",194,"2026-09-29T13:16:04.000Z",{"name":64,"slug":65,"count":66,"latest_published_at":67},"Science","science",154,"2026-09-28T13:19:18.000Z",{"name":69,"slug":70,"count":71,"latest_published_at":72},"Consumer Tech","consumer-tech",142,"2026-09-29T18:38:03.000Z",{"name":74,"slug":75,"count":76,"latest_published_at":77},"Software","software",91,"2026-09-25T20:55:00.000Z",{"name":79,"slug":80,"count":81,"latest_published_at":82},"Dev Tools","dev-tools",89,"2026-09-29T17:15:00.000Z",{"name":84,"slug":85,"count":86,"latest_published_at":87},"Startups","startups",83,"2026-09-29T21:51:36.000Z",{"name":89,"slug":90,"count":91,"latest_published_at":92},"General","general",49,"2026-09-28T16:44:57.000Z",{"name":94,"slug":95,"count":96,"latest_published_at":97},"Gaming","gaming",48,"2026-09-25T18:35:21.000Z",{"name":99,"slug":100,"count":101,"latest_published_at":102},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":104,"slug":105,"count":106,"latest_published_at":107},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]