[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-researchers-build-a-ruler-for-ai-models-that-ramble":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},9645,"researchers-build-a-ruler-for-ai-models-that-ramble","Researchers Build a Ruler for AI Models That Ramble","SLIDER uses information theory to flag when an AI model's reasoning step just repeats earlier ones, and the signal can train leaner models.","A new interpretability tool called SLIDER can finally tell you when an AI model's reasoning is just spinning its wheels.\n\nResearchers built SLIDER using partial information decomposition, a method from information theory, to split the information in each reasoning step into three parts: what's genuinely new, what's redundant with earlier steps, and what only makes sense combined with earlier steps. From that split they derive Step-RRI, a score for whether one step is mostly just restating what came before, and Trajectory-RRI, an aggregate score for an entire reasoning chain. On the redundancy portion of the PRMBench dataset, Step-RRI beat embedding-similarity and information-gain baselines by more than 10 points at catching repetitive steps. Across QwQ-32B, DeepSeek-R1-Distill-Qwen-32B, and GPT-4.1, Trajectory-RRI tracked closely with how long each model's reasoning actually ran.\n\nReasoning models are notorious for burning tokens re-deriving the same logic before landing on an answer, and that waste adds up in cost and latency at scale. A measurable, theory-grounded signal for redundancy - rather than an eyeballed \"this looks repetitive\" - gives teams a concrete way to filter training data toward leaner reasoning. The paper reports that fine-tuning on Trajectory-RRI-selected data cut down rambling while largely holding onto task performance.\n\nIt's a diagnostic, not a fix: the paper doesn't claim SLIDER makes a model smarter, only that it tells you exactly where its reasoning is stalling.","[\"ai\",\"llm-reasoning\",\"interpretability\",\"research\"]","2026-10-02T04:00:00.000Z","2026-10-03T04:24:58.325Z","2026-10-03T04:25:03.589Z","published",null,[],"ai",[24,26,27,28],"llm-reasoning","interpretability","research",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.00571",0,{"sections":35},[36,39,43,47,52,56,60,65,70,75,80,85,90,95],{"name":37,"slug":24,"count":38,"latest_published_at":18},"AI",5977,{"name":40,"slug":41,"count":42,"latest_published_at":18},"Security","security",842,{"name":44,"slug":45,"count":46,"latest_published_at":18},"Policy","policy",438,{"name":48,"slug":49,"count":50,"latest_published_at":51},"Deals","deals",317,"2026-10-01T22:00:00.000Z",{"name":53,"slug":54,"count":55,"latest_published_at":18},"Hardware","hardware",199,{"name":57,"slug":58,"count":59,"latest_published_at":18},"Science","science",173,{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",155,"2026-10-01T19:54:10.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Dev Tools","dev-tools",96,"2026-10-01T16:57:03.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Software","software",93,"2026-09-30T21:41:11.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Startups","startups",90,"2026-10-01T21:55:22.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Gaming","gaming",53,"2026-10-02T02:50:39.000Z",{"name":86,"slug":87,"count":88,"latest_published_at":89},"General","general",50,"2026-09-30T21:37:54.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"How-To","how-to",7,"2026-10-01T09:00:00.000Z"]