Model Releases
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 …
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 pro
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. https://arxiv.org/abs/2610.20334 Chat with Paper: https://academy.dair.ai/papers/treeflex-agents-navigating-their-own-search-trees-2610.20334
Related
- New research from Meta and CMU. This one is on agentic context management for long horizon tasks. (bookmark it) Production agents accumulate…
- TreeFlex: Agents Navigating Their Own Search Trees
Source: DAIR.AI (X) | 2026-10-15