TreeFlex: Agents Navigating Their Own Search Trees· TreeFlex：代理自主导航搜索树
A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context. As this context grows, stale and off-path information consumes its limited capacity and obscures relevant evidence, making focused reasoning increasingly difficult. We introduce TreeFlex, a framework in which the agent's own policy decides where to search. The agent records each intermediate state, with a short summary, as a node in a search tree maintained by the harness. The policy is a single language model that acts in two roles. In the Reflection role, it has a global view of the tree through these summaries and picks a node to resume, together with an instruction. In the Execution role, the harness restores the path that led to that node, and the model carries out the instruct
代理通过自主决策搜索树节点，提高长期任务中的专注推理能力。
- 核心方法
- TreeFlex框架将代理的中间状态作为搜索树的节点记录，通过Language Model在Reflection和Execution两个角色间切换来决定搜索的路径与节点。
- 适合谁读
- 研究者 / 工程师
- 要解决的问题
- 在长期任务中，代理的记忆上下文会积累大量无效信息，干扰专注推理。
- 关键实验
- 未提供
- 主要贡献
- 提出了一种新的代理决策框架，允许代理自主管理搜索过程，减少无效信息的干扰。
- 意义与局限
- TreeFlex有助于提高代理在复杂、长期任务中的性能，但需要评估其在不同任务中的泛化能力和计算成本。