[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-researchers-fix-ai-agents-that-forget-how-to-search-in-parallel":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},7309,"researchers-fix-ai-agents-that-forget-how-to-search-in-parallel","Researchers Fix AI Agents That Forget How to Search in Parallel","A new curriculum called CHART rotates training prompts so AI search agents keep parallel-search skills even when their system prompt changes.","Teach an AI agent to search in parallel, then rewrite its system prompt, and it may quietly forget how.\n\nResearchers studying reinforcement-learning-trained search agents found that models taught to fire off several search queries simultaneously, a technique known as parallel search that boosts both speed and accuracy, tend to learn that skill in a way that is tightly bound to the exact wrapper, or harness, they trained under. The harness is the surrounding scaffolding, things like the system prompt and tool-calling format, that a production app wraps around a model. Change the wording of that prompt and the agent often reverts to slower, one-query-at-a-time serial search, even though the underlying task hasn't changed. Simply training on a bigger variety of harnesses doesn't fix it either: a small set of harnesses gets mastered too quickly to teach the general skill, while a large set spreads the training signal so thin that no single harness fully sticks.\n\nThe fix, called CHART, rotates the training harnesses on a schedule, retiring ones the model has mastered and swapping in fresh, still-difficult ones to keep the learning signal alive. The result: the agent generalizes parallel search across 89% of harnesses it never saw during training, versus at most 5% for the best fixed-pool approach, and it even carries the skill to a new question-answering task and search environment, gaining 5.6 percentage points in accuracy. That matters because production teams rewrite system prompts constantly, and this work suggests a lot of the behavior we assume is 'learned' by an agent is actually just memorized surface pattern-matching to one particular prompt.\n\nIt's a useful reminder that a benchmark score earned under one prompt says less about an agent's actual competence than about how well it memorized that prompt's shape.","[\"ai-agents\",\"reinforcement-learning\",\"search\",\"research\"]","2026-09-23T04:00:00.000Z","2026-09-23T06:40:15.623Z","2026-09-23T06:40:19.620Z","published",null,[],"ai",[26,27,28,29],"ai-agents","reinforcement-learning","search","research",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.22247",0,{"sections":36},[37,40,44,49,54,59,63,68,73,78,83,88,93,98],{"name":38,"slug":24,"count":39,"latest_published_at":18},"AI",4265,{"name":41,"slug":42,"count":43,"latest_published_at":18},"Security","security",707,{"name":45,"slug":46,"count":47,"latest_published_at":48},"Policy","policy",369,"2026-09-23T02:13:52.000Z",{"name":50,"slug":51,"count":52,"latest_published_at":53},"Deals","deals",202,"2026-09-22T23:00:04.000Z",{"name":55,"slug":56,"count":57,"latest_published_at":58},"Hardware","hardware",168,"2026-09-22T23:56:03.000Z",{"name":60,"slug":61,"count":62,"latest_published_at":18},"Science","science",133,{"name":64,"slug":65,"count":66,"latest_published_at":67},"Consumer Tech","consumer-tech",110,"2026-09-22T20:00:00.000Z",{"name":69,"slug":70,"count":71,"latest_published_at":72},"Software","software",80,"2026-09-22T23:32:52.000Z",{"name":74,"slug":75,"count":76,"latest_published_at":77},"Dev Tools","dev-tools",79,"2026-09-22T22:21:13.000Z",{"name":79,"slug":80,"count":81,"latest_published_at":82},"Startups","startups",65,"2026-09-22T22:06:48.000Z",{"name":84,"slug":85,"count":86,"latest_published_at":87},"Gaming","gaming",45,"2026-09-22T15:35:06.000Z",{"name":89,"slug":90,"count":91,"latest_published_at":92},"General","general",43,"2026-09-21T23:48:56.000Z",{"name":94,"slug":95,"count":96,"latest_published_at":97},"Reviews","reviews",27,"2026-09-22T13:00:00.000Z",{"name":99,"slug":100,"count":101,"latest_published_at":102},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]