Pith. sign in

REVIEW 9 cited by

Enhancing LLM Reasoning with Reward-guided Tree Search

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.11694 v4 pith:Z6COCQ6H submitted 2024-11-18 cs.CL cs.AI

classification cs.CLcs.AI
keywords modelreasoningsearchtreeenhancingframeworkllmsabilities
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recently, test-time scaling has garnered significant attention from the research community, largely due to the substantial advancements of the o1 model released by OpenAI. By allocating more computational resources during the inference phase, large language models~(LLMs) can extensively explore the solution space by generating more thought tokens or diverse solutions, thereby producing more accurate responses. However, developing an o1-like reasoning approach is challenging, and researchers have been making various attempts to advance this open area of research. In this paper, we present a preliminary exploration into enhancing the reasoning abilities of LLMs through reward-guided tree search algorithms. This framework is implemented by integrating the policy model, reward model, and search algorithm. It is primarily constructed around a tree search algorithm, where the policy model navigates a dynamically expanding tree guided by a specially trained reward model. The implemented framework is denoted as \textbf{STILL-1}. We thoroughly explore various design considerations necessary for implementing this framework and provide a detailed report of the technical aspects. To assess the effectiveness of our approach, we focus on mathematical reasoning tasks and conduct extensive evaluations on four challenging datasets, significantly enhancing the reasoning abilities of LLMs.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework

    cs.AI 2025-09 conditional novelty 6.0 of 10

    Sticker-TTS uses three collaborating models to distill and reuse compact summaries (stickers) of past reasoning attempts, improving math benchmark accuracy at a claimed equivalent inference cost.

  2. Com$^2$: A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Com2 is a causal-graph-guided benchmark with 3,754 questions showing that LLMs struggle with complex commonsense reasoning, particularly on intervention and transition tasks.

  3. TreeThink: A Modular Tree Search Library for Mathematical Reasoning with LLMs

    cs.CL 2026-07 conditional novelty 5.5 of 10

    TreeThink provides a modular, asynchronous tree-search library for neural theorem proving with unified REPL clients for Lean, Rocq, and Isabelle and up to 6.3× wall-clock speedup.

  4. Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs

    cs.CL 2025-08 unverdicted novelty 5.0 of 10

    The abstract claims a new local search framework for code generation, but the manuscript body is a different mathematics paper.

  5. Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations

    cs.CV 2025-06 conditional novelty 5.0 of 10

    Ctrl-Z Sampling improves text-to-image outputs by adaptively rolling back and re-exploring when a reward model flags a quality plateau, at roughly 3 to 9 times the usual compute.

  6. VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism

    cs.CV 2025-06 conditional novelty 5.0 of 10

    VReST combines Monte Carlo tree search with a self-reward signal inside a vision-language model to get higher accuracy than CoT, ToT, or voting baselines on MathVista, MathVision, and CharXiv, while spending several t...

  7. Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thought

    cs.AI 2025-09 reject novelty 4.0 of 10

    LLM chain-of-thought length converges to an optimum because of an underfitting-overfitting tradeoff, formalized in a continuous reasoning-space framework and tested with RL.

  8. From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR

    cs.CL 2025-08 unverdicted novelty 4.0 of 10

    A systematic analysis of LLM exploration in RLVR, introducing capability-boundary metrics and examining entropy-performance exchange across training stages and token levels.

  9. Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design

    cs.AI 2025-06 conditional novelty 4.0 of 10

    Evaluation conditions like seed, dataset version, and answer ordering cause multi-point benchmark score swings in DeepSeek-R1-Distill and related reasoning models, undermining reliable comparison.

Pith tools