paper-with-me

홈 › Papers

Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning Patterns

2025-05-29 · Xiang Li, Haiyang Yu, Xinghua Zhang, Ziyang Huang, Shizhu He, Kang Liu, Jun Zhao, Fei Huang, Yongbin Li

Process Reward Models (PRMs) are crucial in complex reasoning and problem-solving tasks (e.g., LLM agents with long-horizon decision-making) by verifying the correctness of each intermediate reasoning step. In real-world scenarios, LLMs may apply various reasoning patterns (e.g., decomposition) to solve a problem, potentially suffering from errors under various reasoning patterns. Therefore, PRMs are required to identify errors under various reasoning patterns during the reasoning process. However, existing benchmarks mainly focus on evaluating PRMs with stepwise correctness, ignoring a systematic evaluation of PRMs under various reasoning patterns. To mitigate this gap, we introduce Socratic-PRMBench, a new benchmark to evaluate PRMs systematically under six reasoning patterns, including Transformation, Decomposition, Regather, Deduction, Verification, and Integration. Socratic-PRMBench}comprises 2995 reasoning paths with flaws within the aforementioned six reasoning patterns. Through our experiments on both PRMs and LLMs prompted as critic models, we identify notable deficiencies in existing PRMs. These observations underscore the significant weakness of current PRMs in conducting evaluations on reasoning steps under various reasoning patterns. We hope Socratic-PRMBench can serve as a comprehensive testbed for systematic evaluation of PRMs under diverse reasoning patterns and pave the way for future development of PRMs.

📄 PDF Abstract BibTeX arXiv:2505.23474

Code (0)

등록된 구현이 없습니다.

Tasks

Benchmarking

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents

2026-01-18 · Dawei Li, Yuguang Yao, Zhen Tan, Huan Liu 외 arxiv

Reward-guided search methods have demonstrated strong potential in enhancing tool-using agents by effectively guiding sampling and exploration over complex action spaces. As a core design, those search methods utilize pr…

PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models

2025-01-06 · Mingyang Song, Zhaochen Su, Xiaoye Qu, Jiawei Zhou 외

Process-level Reward Models (PRMs) are crucial for complex reasoning and decision-making tasks, where each intermediate step plays an important role in the reasoning process. Since language models are prone to various ty…

Decision Making

MedPRMBench: A Fine-grained Benchmark for Process Reward Models in Medical Reasoning

2026-04-19 · Lingyan Wu, Xiang Zheng, Weiqi Zhai, Wei Wang 외 arxiv

Process-Level Reward Models (PRMs) are essential for guiding complex reasoning in large language models, yet existing PRM benchmarks cover only general domains such as mathematics, failing to address medical reasoning --…

WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents

2026-01-29 · Yao Zhang, Shijie Tang, Zeyu Li, Zhen Han 외 arxiv

Web agents hold great potential for automating complex computer tasks, yet their interactions involve long-horizon, sequential decision-making with irreversible actions. In such settings, outcome-based supervision is spa…

Reinforcement LearningText Generation

SocraticPO: Policy Optimization via Interactive Guidance

2026-06-03 · Zirui Liu, Jie Ouyang, Qi Liu, Xianquan Wang 외 arxiv

Reinforcement learning (RL) for large language models usually supervises reasoning with scalar outcome rewards, such as binary correctness. Such rewards provide an optimization direction but rarely explain how a model sh…

Reinforcement Learning