[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-selfcompact-jhu-when-to-compress-rubric":3,"news-related-83ef24e7-e2f5-4aec-8b4e-88bd10f8c28c":36},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"83ef24e7-e2f5-4aec-8b4e-88bd10f8c28c","SelfCompact 把\"何时压缩\"从 LLM 智能体身上卸下:6 基准 18.1 分提点,token 成本砍 30-70%","LLM 智能体跑长链路时,CoT + 工具调用轨迹会持续累积陈旧内容、撞穿上下文窗口——这是被忽视的\"上下文腐烂\"。主流做法是按 token 阈值做固定间隔压缩,这种无脑触发常打断推理、丢掉关键中间结果。\n\nJHU 团队 6 月 22 日公开的 arXiv 论文 2606.23525 把这件事拆成两件:一个供模型调用的压缩工具,加一份规定\"何时触发、何时抑制\"的轻量 rubric。两件缺一不可——只有工具时开源模型要么乱用要么不用,只有 rubric 时又动不了手。\n\n6 个数学 + agentic 搜索基准、7 个模型的实验显示,SelfCompact 用远低于固定间隔策略的 token 成本达到或超过其表现:相比完全不压缩基线,数学任务最高提点 18.1,agentic 搜索提点 5-9,单题成本下降 30-70%。\n\n最值得玩味的结论是\"元认知缺口\":当下 LLM 不可靠地判断上下文是否烂掉,但一条 30 行左右的 rubric 就能补上。\"何时该忘\"不该是 LLM 的内禀能力,而应是脚手架外接的能力——agent 系统的天花板,正从\"训练更大的模型\"转向\"写更好的脚手架\"。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.23525","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"6ad31a14-c0da-42df-81fd-564281f768db","agentic-ai",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",{"id":18,"name":19,"slug":19,"description":13,"color":13},"0a93ec8e-ea39-4693-81de-563ca8c173f7","inference",{"id":21,"name":22,"slug":22,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"991a105e-30a3-4907-84ff-60b1de895a80","en","SelfCompact decides when to compress, 30-70% fewer tokens","arXiv 2606.23525 introduces SelfCompact, a context-compression framework for LLM Agents that decides \"when to compress\" automatically, removing the burden from the Agent itself. The result: +18.1 average points across 6 long-horizon Agent benchmarks, with 30-70% token cost reduction.\n\nThe problem: LLM Agents that handle long-horizon tasks (e.g., 100+ turns of conversation) face a context-window overflow. The Agent must decide \"when to compress\" — too early, and you lose important information; too late, and you run out of context. This \"when to compress\" decision is itself a hard problem, and existing Agents either compress too aggressively (losing information) or too late (overflowing context).\n\nSelfCompact's fix: a separate \"compression controller\" (a small 1.5B model) that monitors the Agent's context in real time and decides when to compress. The controller is trained with a reinforcement signal: compress when it would improve downstream task performance, don't compress when it would hurt. The training data is generated by running Agents on long-horizon tasks and observing the optimal compression points.\n\nThe result: SelfCompact improves Agent accuracy by 18.1 points on average across 6 benchmarks (WebShop, ALFWorld, ToolBench, etc.), while reducing token consumption by 30-70%. The biggest improvement is on tasks where the Agent must remember specific details from many turns ago.\n\nThe bigger takeaway: \"compression as a separate module\" is the right architecture. Most current Agents handle compression inline, which is a distraction from the main task. SelfCompact's separate controller is a cleaner design, and the RL-trained compression policy is significantly more accurate than heuristic-based compression. For the industry, this means the next generation of Agent frameworks will have \"compression\" as a first-class, separately-trained component.","selfcompact-jhu-when-to-compress-rubric","2026-06-23T08:00:00Z","2026-06-23T16:13:35.988220Z","2026-08-19T02:08:40.142862Z",true,"agent",108,{"items":37},[38,43,48,53,58,63],{"id":39,"title":40,"news_slug":41,"published_at":42},"6784d3bd-26c1-4fd5-a2e5-8c7b9e591dae","SmoothAgent 把上下文变换「提前做」：Agent 长链路 TTFT 砍到原来的 1\u002F12","smoothagent-ttft-12x","2026-07-23T03:00:00+00:00",{"id":44,"title":45,"news_slug":46,"published_at":47},"5988b398-8533-4af5-9aca-ff6e51e9f429","Parallel-Synthesis：让 KV Cache 成为 Agent 多分支的「原生合成接口」，TTFT 提速 2.5–11×","parallel-synthesis-kv-cache-agent-2-5-11x","2026-06-15T14:00:00+00:00",{"id":49,"title":50,"news_slug":51,"published_at":52},"c0fdcd77-4585-4b04-b042-ddf1789c2158","AI模型发布逻辑正在重写：2026年5月，四条主线改变竞争规则","may-2026-4-main-lines-competition-rewrite","2026-05-27T00:15:00+00:00",{"id":54,"title":55,"news_slug":56,"published_at":57},"cac485ab-a429-4ebc-88c6-a1f924f978ff","AWS 开源 KeysAndValues:微调时就让模型学会“遗忘”,单张 A100 撑住 128K","aws-keysvalues-sparse-attention-finetuning","2026-08-26T05:20:00+00:00",{"id":59,"title":60,"news_slug":61,"published_at":62},"c94bdf86-5de9-49fe-8c98-0f5c47611bfe","SGLang v0.5.18 发布:大模型冷启动提速 2.38 倍,710 个 PR 都改了什么","sglang-v0-5-18-cold-start-2-38x","2026-08-24T23:15:00+00:00",{"id":64,"title":65,"news_slug":66,"published_at":67},"f65e204c-0115-4b50-9113-2c3bb2ff6637","ReCache:给 Agent 的工具记忆装上独立缓存,KV 内存砍 92%、首 token 提速 3.655 倍","recache-agent-kv-cache-reuse","2026-08-24T15:30:00+00:00"]