Meta和CMU的新研究：智能体自己管理上下文，不再傻傻丢东西。在BrowseComp-Plus上提升了27%，代码已开源，值得看看。
Meta和CMU联合提出ACM（Agentic Context Management）方法，用于长周期智能体任务。传统方法按token阈值压缩并丢弃上下文，ACM让智能体自主决策何时压缩，将丢弃内容存入外部记忆并可查询。基于高质量演示的后训练pipeline在BrowseComp-Plus基准上取得27%相对提升，性能接近比它大40倍的开源模型。代码、数据和checkpoint已开源。
New research from Meta and CMU. This one is on agentic context management for long horizon tasks. ...
New research from Meta and CMU. This one is on agentic context management for long horizon tasks. (bookmark it) Production agents accumulate context every turn. The usual fix compresses on a token threshold and throws the remainder away, so the trigger sometimes fires for reasons unrelated to what the agent is currently working on. ACM hands the agent purpose-built context editing tools. It decides when to compress, offloads what it drops into an external memory store, and queries that store later when it needs the detail back. Compression shifts from short-term to long-term memory. They also build a post-training pipeline on high-quality context management demonstrations. That yields a 27% relative gain on BrowseComp-Plus and gets close to open-source models 40 times larger. Better context management lowers peak token pressure, lets the agent explore longer before running out of room, and produces more consistent solutions across independent trials of the same task. Code, data, and checkpoints are released. Paper: arxiv.org/abs/2607.23809 Learn to build effective AI agents in our academy: academy.dair.ai 💬 10 🔄 17 ❤️ 83 👀 6970 📊 33 ⚡