Policy Guided Tree Search for Enhanced LLM Reasoning

• URL: http://arxiv.org/abs/2502.06813v1
• Date: Tue, 04 Feb 2025 22:08:20 GMT
• Title: Policy Guided Tree Search for Enhanced LLM Reasoning
• Authors: Yang Li,
• Abstract summary: Policy-Guided Tree Search (PGTS) is a framework that combines reinforcement learning with structured tree exploration to efficiently navigate reasoning paths. Our key innovation is a learned policy that dynamically decides between expanding, branching, backtracking, or terminating exploration, eliminating the need for manuals or exhaustive search.
• Score: 3.090041654375235
• License:
• Abstract: Despite their remarkable capabilities, large language models often struggle with tasks requiring complex reasoning and planning. While existing approaches like Chain-of-Thought prompting and tree search techniques show promise, they are limited by their reliance on predefined heuristics and computationally expensive exploration strategies. We propose Policy-Guided Tree Search (PGTS), a framework that combines reinforcement learning with structured tree exploration to efficiently navigate reasoning paths. Our key innovation is a learned policy that dynamically decides between expanding, branching, backtracking, or terminating exploration, eliminating the need for manual heuristics or exhaustive search. Experiments across mathematical reasoning, logical deduction, and planning benchmarks demonstrate that PGTS achieves superior reasoning performance while significantly reducing computational costs compared to existing methods. These results establish PGTS as a scalable and effective solution for tackling complex reasoning tasks with LLMs.

Related papers

• Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures [0.0]
  We introduce Adaptive Graph of Thoughts (AGoT), a dynamic, graph-based inference framework. AGoT enhances Large Language Models (LLMs) reasoning solely at test time. We validate our approach on diverse benchmarks spanning multi-hop retrieval, scientific reasoning, and mathematical problem-solving.
  arXiv  Detail & Related papers  (2025-02-07T16:54:19Z)
• RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement [85.08223786819532]
  Existing large language models (LLMs) show exceptional problem-solving capabilities but might struggle with complex reasoning tasks. We propose textbfRAG-Star, a novel RAG approach that integrates retrieved information to guide the tree-based deliberative reasoning process. Our experiments involving Llama-3.1-8B-Instruct and GPT-4o demonstrate that RAG-Star significantly outperforms previous RAG and reasoning methods.
  arXiv  Detail & Related papers  (2024-12-17T13:05:36Z)
• Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning [40.069109287947875]
  We propose a novel reasoning framework called Forest-of-Thought (FoT) FoT integrates multiple reasoning trees to leverage collective decision-making for solving complex logical problems. We introduce a dynamic self-correction strategy that enables real-time error correction, along with consensus-guided decision-making strategies.
  arXiv  Detail & Related papers  (2024-12-12T09:01:18Z)
• Enhancing LLM Reasoning with Reward-guided Tree Search [95.06503095273395]
  o1-like reasoning approach is challenging, and researchers have been making various attempts to advance this open area of research. We present a preliminary exploration into enhancing the reasoning abilities of LLMs through reward-guided tree search algorithms.
  arXiv  Detail & Related papers  (2024-11-18T16:15:17Z)
• LiteSearch: Efficacious Tree Search for LLM [70.29796112457662]
  This study introduces a novel guided tree search algorithm with dynamic node selection and node-level exploration budget. Experiments conducted on the GSM8K and TabMWP datasets demonstrate that our approach enjoys significantly lower computational costs compared to baseline methods.
  arXiv  Detail & Related papers  (2024-06-29T05:14:04Z)
• What Matters in Hierarchical Search for Combinatorial Reasoning Problems? [0.5007502976837217]
  Recent efforts have sought to enhance planning by incorporating hierarchical high-level search strategies, known as subgoal methods. While promising, their performance against traditional low-level planners is inconsistent, raising questions about their application contexts. We identify the attributes pivotal for leveraging the advantages of high-level search: hard-to-learn value functions, complex action spaces, presence of dead ends in the environment, or using data collected from diverse experts.
  arXiv  Detail & Related papers  (2024-06-05T15:14:58Z)
• Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing [61.98556945939045]
  We propose a framework to learn planning-based reasoning through Direct Preference Optimization (DPO) on collected trajectories. Our results on challenging logical reasoning benchmarks demonstrate the effectiveness of our learning framework.
  arXiv  Detail & Related papers  (2024-02-01T15:18:33Z)
• PathFinder: Guided Search over Multi-Step Reasoning Paths [80.56102301441899]
  We propose PathFinder, a tree-search-based reasoning path generation approach. It enhances diverse branching and multi-hop reasoning through the integration of dynamic decoding. Our model generalizes well to longer, unseen reasoning chains, reflecting similar complexities to beam search with large branching factors.
  arXiv  Detail & Related papers  (2023-12-08T17:05:47Z)
• When Do Program-of-Thoughts Work for Reasoning? [51.2699797837818]
  We propose complexity-impacted reasoning score (CIRS) to measure correlation between code and reasoning abilities. Specifically, we use the abstract syntax tree to encode the structural information and calculate logical complexity. Code will be integrated into the EasyInstruct framework at https://github.com/zjunlp/EasyInstruct.
  arXiv  Detail & Related papers  (2023-08-29T17:22:39Z)

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.