Meta AI 提出 TreeFlex 框架让智能体自主管理搜索
DAIR.AI 介绍 Meta AI 的新工作 TreeFlex，一个让智能体自身策略决定如何搜索的框架。针对 ReAct 把每次失败尝试都留在同一上下文、导致有用证据难找的问题，TreeFlex 将每个中间状态存为搜索树节点，同一模型读取所有节点的简短摘要来决定继续搜索、分支、检查答案或停止。
New work from Meta AI on agents that manage their own search.
(bookmark it)
A ReAct agent keeps every failed attempt in one context, making useful evidence harder to find.
To improve on this, they propose TreeFlex, a framework in which the agent’s own policy decides where to search.
In TreeFlex, the agent saves each intermediate state as a node in a search tree. The same model then reads short summaries of all nodes and decides where to continue, whether to branch, when to check a proposed answer, and when to stop.
On a deep-research benchmark, a 4B model reaches 48.8% versus 41.5% for flat ReAct, at the same context limit.
Same 9B base model, both trained with RL. 54.9% on SWE-bench Verified with TreeFlex, versus 43.3% with FoldAgent.
arxiv.org/abs/2610.20334
Chat with Paper: academy.dair.ai/papers/treef…
来源：dair_ai · x.com