# TreeSeeker： 树结构试错与返回的深度搜索框架

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-10 08:00
- AIHOT 分数：48
- AIHOT 链接：https://aihot.virxact.com/items/cmqap4xzd0njfslld24c34qfj
- 原文链接：https://arxiv.org/abs/2606.11662

## AI 摘要

TreeSeeker是一种推理时框架，通过树结构状态组织深度搜索中的分支与回退。每回合利用文本UCB信号（价值、不确定性、风险）选择利用有前途的分支、探索不确定替代或剪枝无效路径并返回早期分支点。TreeMem将证据、不确定性、冲突、进度和失败线索附加到产生它们的分支上。在XBench-DeepSearch、BrowseComp和BrowseComp-ZH基准上，TreeSeeker持续优于强开源基线，表明显式的分支-回退控制可增强更强推理与工具执行能力。

## 正文

Deep search requires agents to answer complex questions through multi-step web search, browsing, evidence comparison, and synthesis. A central challenge is deciding how to search when several directions look plausible but only some will later lead to reliable evidence. If an agent greedily follows the current best-looking direction, it may keep extending a weak continuation. If it explores without discipline, it may waste budget on disconnected trials. We propose TreeSeeker, an inference-time framework for controlled trial-and-error in deep search. TreeSeeker organizes search as branch-and-return search over tree-structured states, where each branch is a tentative direction for a sub-goal. At each round, TreeSearch reads all sub-goal trees, identifies active goals, and uses textual UCB signals of value, uncertainty, and risk to select among exploiting a promising branch, exploring an uncertain alternative, or pruning an unproductive continuation and returning to an earlier branch point. TreeMem supports this control loop by keeping evidence, uncertainty, conflicts, progress, and failure cues attached to the branches that produced them, so trial outcomes can guide later decisions. Experiments on XBench-DeepSearch, BrowseComp, and BrowseComp-ZH show that TreeSeeker consistently outperforms strong open-source baselines, suggesting that explicit branch-and-return control complements stronger reasoning and tool execution.