[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-llms-that-manage-their-own-memory":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},3198,"llms-that-manage-their-own-memory","LLMs That Manage Their Own Memory","A new system called Self-GC lets long-running AI agents govern their own context like a garbage collector, cutting token use without losing critical state.","Long-running AI agents now have a smarter way to forget.\n\nResearchers have proposed Self-GC, a context management system for large language model agents that handle extended, multi-step tasks. Instead of relying on blunt heuristics — like dropping the oldest messages or summarizing everything near a context limit — Self-GC treats each user turn, tool result, and skill state as an indexed object with a lifecycle. A side-channel planner proposes what to fold, mask, or prune; a harness enforces those decisions while keeping recoverable copies. The result: the agent sheds dead weight without accidentally discarding something it will need later.\n\nThe numbers are meaningful. On a 33-session hard test set, Self-GC pruned 43.95% of prefix tokens while leaving 84.85% of future continuations unaffected — well above the 54.55% to 69.70% no-impact rates from heuristic baselines. On a larger 332-session production-derived suite, the system reached no-impact rates of 91.27% to 94.58%, versus 77.71% to 87.46% for baselines. In a live online split, it cut daytime average input tokens by 10% to 15%, with peaks near 20%.\n\nContext windows have grown enormous — Gemini 1.5 and others now offer millions of tokens — but raw capacity doesn't solve the problem of what to do with a sprawling agent state mid-task. Stuffing everything in and hoping the model attends to the right parts is expensive and error-prone. Self-GC is a bet that agents need runtime lifecycle control, not just a bigger bucket.\n\nSelf-governing memory sounds appealing until you remember that the planner deciding what to prune is itself an LLM — so the system's reliability ultimately rests on one model trusting another to not throw away the wrong thing.","[\"ai\",\"llm\",\"context-management\",\"research\"]","2026-07-02T04:00:00.000Z","2026-07-02T04:21:05.472Z","2026-07-02T04:21:08.353Z","published",null,[],"ai",[24,26,27,28],"llm","context-management","research",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.00692",0,{"sections":35},[36,40,45,50,55,60,65,70,75,80,85,89,94,99],{"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":72,"count":73,"latest_published_at":74},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Dev Tools","dev-tools",59,"2026-07-07T04:00:00.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":86,"slug":87,"count":83,"latest_published_at":88},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":95,"slug":96,"count":97,"latest_published_at":98},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]