paper-with-me

홈 › Papers

Accurate and Diverse LLM Mathematical Reasoning via Automated PRM-Guided GFlowNets

2025-04-28 · Adam Younsi, Abdalgader Abubaker, Mohamed El Amine Seddik, Hakim Hacid, Salem Lahlou

Achieving both accuracy and diverse reasoning remains challenging for Large Language Models (LLMs) in complex domains like mathematics. A key bottleneck is evaluating intermediate reasoning steps to guide generation without costly human annotations. To address this, we first introduce a novel Process Reward Model (PRM) trained automatically using Monte Carlo Tree Search coupled with a similarity-based data augmentation technique, effectively capturing step-level reasoning quality. Leveraging this PRM, we then adapt Generative Flow Networks (GFlowNets) to operate at the reasoning step level. Unlike traditional reinforcement learning focused on maximizing a single reward, GFlowNets naturally sample diverse, high-quality solutions proportional to their rewards, as measured by our PRM. Empirical evaluation shows strong improvements in both accuracy and solution diversity on challenging mathematical benchmarks (e.g., +2.59% absolute accuracy on MATH Level 5 for Llama3.2-3B), with effective generalization to unseen datasets (+9.4% absolute on SAT MATH). Our work demonstrates the potential of PRM-guided, step-level GFlowNets for developing more robust and versatile mathematical reasoning in LLMs.

📄 PDF Abstract BibTeX arXiv:2504.19981

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationDiversityMathMathematical Reasoning

Similar Papers 제목 키워드 기반

ReDiPPO: Reference-Guided Value Calibration and Discrepancy-Aware Token Reweighting for Mathematical Reasoning

2026-07-30 · Zhenrong Zhang, Fei Wu, Jun Du, Jianshu Zhang 외 arxiv

Reinforcement learning has emerged as an effective paradigm for enhancing the mathematical reasoning capabilities of large language models. Among existing policy optimization methods, Proximal Policy Optimization (PPO) r…

Reinforcement LearningMathematical Reasoning

RADAR: A Reasoning-Guided Attribution Framework for Explainable Visual Data Analysis

2025-08-23 · Anku Rani, Aparna Garimella, Apoorv Saxena, Balaji Vasan Srinivasan 외 arxiv

Data visualizations like charts are fundamental tools for quantitative analysis and decision-making across fields, requiring accurate interpretation and mathematical reasoning. The emergence of Multimodal Large Language …

Mathematical ReasoningAnswer Generation

Limits of PRM-Guided Tree Search for Mathematical Reasoning with LLMs

2025-10-23 · Tristan Cinquin, Geoff Pleiss, Agustinus Kristiadi arxiv

While chain-of-thought prompting with Best-of-N (BoN) selection has become popular for mathematical reasoning in large language models (LLMs), its linear structure fails to capture the branching and exploratory nature of…

Mathematical Reasoning

CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning

2026-04-16 · Zhuo Wang, Zhuo Zhang, Yafu Li, Yu Cheng 외 arxiv

Large Language Models (LLMs) exhibit strong mathematical reasoning when trained on high-quality Chain-of-Thought (CoT) that articulates intermediate steps, yet costly CoT curation hinders further progress. While existing…

Mathematical Reasoning

Enhancing LLM Reasoning with Reward-guided Tree Search

2024-11-18 · Jinhao Jiang, Zhipeng Chen, Yingqian Min, Jie Chen 외

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 durin…

Mathematical Reasoning