TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search

• URL: http://arxiv.org/abs/2606.11662v1
• Date: Wed, 10 Jun 2026 05:10:19 GMT
• Title: TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search
• Abstract summary: TreeSeeker is an inference-time framework for controlled trial-and-error in deep search.<n>It organizes search as branch-and-return search over tree-structured states, where each branch is a tentative direction for a sub-goal.<n>TreeSeeker consistently outperforms strong open-source baselines.
• Score: 43.554579524244495
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Self-Correcting Long-Horizon Search Agents via Tree-Structured Memory [20.351040137738398]
  We propose ReTree, a self-correcting tree-structured memory mechanism for search agents.<n>ReTree constructs a bounded per-step reasoning context while preserving source-linked evidence.<n>Experiments on four public question-answering and search benchmarks show that ReTree consistently outperforms Full-Trajectory ReAct.
  arXiv  Detail & Related papers  (2026-08-11T08:56:42Z)
• Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents [63.2133766267587]
  Deep search agents answer difficult information-seeking questions by iteratively issuing search queries to gather supporting evidence.<n>We study these questions through a trajectory-level diagnosis of long-horizon search agents.<n>We evaluate the evidence retrieved at each search step and separate two stages of agent behavior: what evidence an agent retrieves and how effectively it uses that evidence.
  arXiv  Detail & Related papers  (2026-08-03T08:46:48Z)
• Toward Generalist Autonomous Research via Hypothesis-Tree Refinement [150.99641031769633]
  We introduce Arbor, a framework for autonomous research that combines a long-lived coordinator, short-lived executors, and Hypothesis Tree Refinement (HTR)<n>As results return, Arbor updates the tree, propagates reusable lessons, refines the search frontier, and admits verified improvements.
  arXiv  Detail & Related papers  (2026-06-10T10:57:05Z)
• Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction [127.64173950476702]
  We study direct corpus interaction (DCI), where an agent searches the raw corpus directly with general-purpose terminal tools.<n>This approach requires no offline indexing and adapts naturally to evolving local corpora.<n>Across IR benchmarks and end-to-end agentic search tasks, this simple setup substantially outperforms strong sparse, dense, and reranking baselines.
  arXiv  Detail & Related papers  (2026-05-03T19:13:11Z)
• Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback [22.721204992834092]
  We show that Transformers are theoretically expressive enough to implement distinct search strategies and can be trained from scratch to approximate those strategies.<n>Our Transformer models exhibit the possibility of generalizing to unseen conditions such as longer horizons or deeper trees.
  arXiv  Detail & Related papers  (2026-03-25T19:50:32Z)
• TreePS-RAG: Tree-based Process Supervision for Reinforcement Learning in Agentic RAG [71.06073770344732]
  Agentic retrieval-augmented generation (RAG) formulates question answering as a multi-step interaction between reasoning and information retrieval.<n>We present TreePS-RAG, an online, tree-based RL framework for agentic RAG that enables step-wise credit assignment while retaining outcome-only rewards.
  arXiv  Detail & Related papers  (2026-01-11T14:07:30Z)
• Tree Search for LLM Agent Reinforcement Learning [23.7084695563981]
  Tree-based Group Relative Policy Optimization (Tree-GRPO) is a grouped agent RL method based on tree search.<n>By sharing common prefixes, the tree search sampling increases the number of rollouts achievable.<n>We demonstrate that the objective of intra-tree level group relative policy optimization is equivalent to that of step-level direct preference learning.
  arXiv  Detail & Related papers  (2025-09-25T14:37:09Z)
• ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search [77.55575655986252]
  ProtInvTree is a reward-guided tree-search framework for protein inverse folding.<n>It reformulates sequence generation as a deliberate, step-wise decision-making process.<n>It supports flexible test-time scaling by expanding the search depth and breadth without retraining.
  arXiv  Detail & Related papers  (2025-06-01T09:34:20Z)
• TreeRare: Syntax Tree-Guided Retrieval and Reasoning for Knowledge-Intensive Question Answering [10.597526246308938]
  Iterative and adaptive retrieval has been shown to be a promising approach to resolve complex, knowledge-intensive questions.<n>We propose TreeRare, a framework that utilizes syntax trees to guide information retrieval and reasoning for question answering.<n>TreeRare achieves substantial improvements over existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-05-31T01:07:50Z)
• Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls [83.89771461061903]
  Recent advancements in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs)<n>Recent advancements in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs)<n>We identify two key challenges contributing to this inefficiency: $textitover-exploration$ due to redundant states with semantically equivalent content, and $textitunder-exploration$ caused by high variance in verifier scoring.<n>We propose FETCH, a flexible, plug-and-play system compatible with various tree search algorithms.
  arXiv  Detail & Related papers  (2025-02-16T16:12:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.