[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-new-survey-maps-the-messy-state-of-ai-agent-reasoning":10,"sections":41},{"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":36,"feedback":40,"feedback_at":22,"cost_usd":40,"total_tokens":40},7389,"new-survey-maps-the-messy-state-of-ai-agent-reasoning","New Survey Maps the Messy State of AI Agent Reasoning","A new arXiv survey maps agentic AI reasoning into three tiers and admits multi-agent coordination and deployment governance remain unsolved.","A new arXiv survey tries to map every corner of agentic AI reasoning, and the result reads like a catalogue of how unsettled the field still is.\n\nResearchers organized agentic reasoning into three layers: foundational reasoning, covering core single-agent skills like planning, tool use, and search in stable environments; self-evolving reasoning, where agents refine those skills through feedback, memory, and adaptation; and collective multi-agent reasoning, which covers coordination and shared goals across multiple agents. The paper also separates in-context reasoning, which scales performance through prompting and orchestration at run time, from post-training reasoning, which shapes behavior via reinforcement learning and fine-tuning. It reviews frameworks used in science, robotics, healthcare, autonomous research, and math. It closes with a list of open problems, including personalization, long-horizon interaction, world modeling, scalable multi-agent training, and governance for real-world deployment.\n\nThis is a taxonomy, not a product launch, but the framing is useful precisely because \"agent\" has become marketing shorthand for anything with a tool-calling loop bolted on. Separating single-agent tool use from genuinely coordinated, collective multi-agent systems gives buyers and builders a sharper vocabulary for what a given \"agentic\" product actually does.\n\nThe most telling part of the paper is its own to-do list: the authors name scalable multi-agent training and real-world governance as unresolved, not solved. Worth remembering next time a demo shows a swarm of agents working in perfect harmony.","[\"ai agents\",\"llm reasoning\",\"research\",\"multi-agent systems\"]","2026-09-23T04:00:00.000Z","2026-09-23T11:04:15.229Z","2026-09-23T11:04:21.800Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"Drop or source the specific claim that multi-agent systems don't scale 'beyond a handful of bots' — the source only says scalable multi-agent training is an open challenge, it doesn't state any current numeric limit.","resolved","ai",[32,33,34,35],"ai agents","llm reasoning","research","multi-agent systems",[37],{"name":38,"url":39},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.12538",0,{"sections":42},[43,46,50,54,59,63,68,73,78,83,88,93,98,103],{"name":44,"slug":30,"count":45,"latest_published_at":18},"AI",4344,{"name":47,"slug":48,"count":49,"latest_published_at":18},"Security","security",713,{"name":51,"slug":52,"count":53,"latest_published_at":18},"Policy","policy",370,{"name":55,"slug":56,"count":57,"latest_published_at":58},"Deals","deals",206,"2026-09-23T09:43:46.000Z",{"name":60,"slug":61,"count":62,"latest_published_at":18},"Hardware","hardware",169,{"name":64,"slug":65,"count":66,"latest_published_at":67},"Science","science",134,"2026-09-23T09:00:00.000Z",{"name":69,"slug":70,"count":71,"latest_published_at":72},"Consumer Tech","consumer-tech",110,"2026-09-22T20:00:00.000Z",{"name":74,"slug":75,"count":76,"latest_published_at":77},"Software","software",81,"2026-09-23T09:56:13.000Z",{"name":79,"slug":80,"count":81,"latest_published_at":82},"Dev Tools","dev-tools",79,"2026-09-22T22:21:13.000Z",{"name":84,"slug":85,"count":86,"latest_published_at":87},"Startups","startups",65,"2026-09-22T22:06:48.000Z",{"name":89,"slug":90,"count":91,"latest_published_at":92},"Gaming","gaming",45,"2026-09-22T15:35:06.000Z",{"name":94,"slug":95,"count":96,"latest_published_at":97},"General","general",43,"2026-09-21T23:48:56.000Z",{"name":99,"slug":100,"count":101,"latest_published_at":102},"Reviews","reviews",27,"2026-09-22T13:00:00.000Z",{"name":104,"slug":105,"count":106,"latest_published_at":107},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]