TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search
Quick Answer
TreeSeeker introduces a framework for controlled trial-and-error in deep search, outperforming strong baselines on XBench-DeepSearch and BrowseComp benchmarks.
Quick Take
By organizing search as a branch-and-return process, it effectively manages exploration and exploitation, leading to better decision-making in complex web searches.
Key Points
- TreeSeeker organizes search as branch-and-return over tree-structured states.
- It uses textual UCB signals to balance exploration and exploitation.
- Experiments show consistent performance improvement over open-source baselines.
- TreeMem supports decision-making by retaining evidence and uncertainty cues.
- The framework addresses the challenge of navigating multiple plausible search directions.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 11662v1 Announce Type: new Abstract: 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.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.