Policy Guided Tree Search for Enhanced LLM Reasoning
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:AJFYYQWHrecord.jsonopen to challenge →
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing
Local Branch Routing (LBR) is a token-level framework for test-time scaling in language models that uses local branch hidden states for routing and supports end-to-end RL, showing gains in Pass@1 and Pass@32 on math r...
-
Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing
LBR performs token-level test-time scaling via local branch routing on hidden states, enabling end-to-end RL training and improving Pass@1 and Pass@32 on math benchmarks over CoT and RLVR baselines.
-
MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
MILES dynamically expands step-wise memory with learnable selection heads that rerank candidates and guide reasoning, improving LLM test-time performance under limited supervision.
-
AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents
AlphaMemo equips LLM alpha-mining agents with AST-diff motif memory, residual learning, and asymmetric veto control to improve out-of-sample factor discovery on CSI 500 and S&P 500.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.