[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-ed39ed38-b5fa-4f58-92cf-d05233ab998b":3},{"id":4,"title":5,"summary":6,"original_url":7,"source_id":8,"tags":9,"published_at":23,"created_at":24,"modified_at":25,"is_published":26,"publish_type":27,"image_url":13,"view_count":28},"ed39ed38-b5fa-4f58-92cf-d05233ab998b","把 LLM Agent 的投机执行变成「有状态加速」:7月14日 arXiv「Speculate with Memory」让推理无损拉满 2.5×、准确率涨 39 个百分点","\"7月14日,arXiv:2607.12236「Speculate with Memory」把记忆系统搬进 LLM Agent 投机执行器,给\\\"无状态推测\\\"补上在线学习能力。核心是在投机器上加三层串联的在线记忆:对比转换表记录历史动作-动作统计分布,情景记忆回溯与当前上下文相似的过往轨迹片段,困惑跟踪器专门压制反复出现的错误。三者协作,让投机器第一次具备了\\\"走过一遍,下次更准\\\"的能力。\\n\\n实验在 6 个基准上覆盖动作预测、观察预测、链路预测三类场景。结果:动作预测准确率相对提升 19-39%;动作重复度高的观察预测任务上,最高取得 2.5× 绝对加速。论文特别强调所有增益\\\"无损\\\"——投机完全跑在环境空闲时段,actor 轨迹与无投机执行完全一致,零额外 wall-clock 开销;且增益随记忆增长持续累积,在不同成本档位的推测器之间都泛化。\\n\\n真正的价值在于把\\\"专项加速\\\"和\\\"持续学习\\\"焊到同一条管道。当前 LLM Agent 的工具调用、环境观察、动作规划彼此耦合,延迟叠加非常夸张;大多数加速方案只关注参数或蒸馏。本文思路相当于把\\\"老司机的肌肉记忆\\\"嵌入推理回路——同一份推理预算,体验越来越好。这种\\\"边际成本递减\\\"的加速路线,比单纯放大模型更可持续,也更贴近 GPU 利用率的真实瓶颈。\\n\\n边界也明确:动作空间越开放,记忆命中率反而下降,而 Agent 越来越走向开放场景。但\\\"轻量记忆 + 投机解码\\\"组合,给所有做 Agent serving 的团队提供了低成本、可借鉴的工程模板,结合 vLLM、SGLang 现成的投机解码接口,很快就能复刻。\\n\"","https:\u002F\u002Farxiv.org\u002Fpdf\u002F2607.12236","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},"7ac06d8e-b074-4147-abfc-ffaa4c6b8744","ai-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","2026-07-15T08:15:00Z","2026-07-15T08:18:21.865304Z","2026-07-15T08:18:21.865314Z",true,"agent",2]