Discriminative Policy Optimization for Token-Level Reward Models

• URL: http://arxiv.org/abs/2505.23363v1
• Date: Thu, 29 May 2025 11:40:34 GMT
• Title: Discriminative Policy Optimization for Token-Level Reward Models
• Authors: Hongzhan Chen, Tao Yang, Shiping Gao, Ruijun Chen, Xiaojun Quan, Hongtao Tian, Ting Yao,
• Abstract summary: Process reward models (PRMs) provide more nuanced supervision compared to outcome reward models (ORMs)<n>Q-RM explicitly learns token-level Q-functions from preference data without relying on fine-grained annotations.<n>Reinforcement learning with Q-RM significantly enhances training efficiency, achieving convergence 12 times faster than ORM on GSM8K and 11 times faster than step-level PRM on MATH.
• Score: 55.98642069903191
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Process reward models (PRMs) provide more nuanced supervision compared to outcome reward models (ORMs) for optimizing policy models, positioning them as a promising approach to enhancing the capabilities of LLMs in complex reasoning tasks. Recent efforts have advanced PRMs from step-level to token-level granularity by integrating reward modeling into the training of generative models, with reward scores derived from token generation probabilities. However, the conflict between generative language modeling and reward modeling may introduce instability and lead to inaccurate credit assignments. To address this challenge, we revisit token-level reward assignment by decoupling reward modeling from language generation and derive a token-level reward model through the optimization of a discriminative policy, termed the Q-function Reward Model (Q-RM). We theoretically demonstrate that Q-RM explicitly learns token-level Q-functions from preference data without relying on fine-grained annotations. In our experiments, Q-RM consistently outperforms all baseline methods across various benchmarks. For example, when integrated into PPO/REINFORCE algorithms, Q-RM enhances the average Pass@1 score by 5.85/4.70 points on mathematical reasoning tasks compared to the ORM baseline, and by 4.56/5.73 points compared to the token-level PRM counterpart. Moreover, reinforcement learning with Q-RM significantly enhances training efficiency, achieving convergence 12 times faster than ORM on GSM8K and 11 times faster than step-level PRM on MATH. Code and data are available at https://github.com/homzer/Q-RM.

Related papers

• ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs [56.32212611983997]
  We introduce ReasonFlux-PRM, a novel trajectory-aware PRM to evaluate trajectory-response type of reasoning traces.<n>ReasonFlux-PRM incorporates both step-level and trajectory-level supervision, enabling fine-grained reward assignment aligned with structured chain-of-thought data.<n>Our derived ReasonFlux-PRM-7B yields consistent performance improvements, achieving average gains of 12.1% in supervised fine-tuning, 4.5% in reinforcement learning, and 6.3% in test-time scaling.
  arXiv  Detail & Related papers  (2025-06-23T17:59:02Z)
• From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling [32.72867198629561]
  We investigate the interplay between pre-training and reward model training FLOPs to assess their influence on PRM efficiency and accuracy.<n>Our findings indicate that PRMs trained on mathematical datasets exhibit performance comparable to those tailored for code generation.
  arXiv  Detail & Related papers  (2025-05-24T12:44:15Z)
• RM-R1: Reward Modeling as Reasoning [81.50471199906738]
  Reasoning Reward Models (ReasRMs) formulate reward modeling as a reasoning task.<n>We propose a reasoning-oriented training pipeline and train a family of ReasRMs, RM-R1.<n>Our models achieve state-of-the-art performance across three reward model benchmarks on average.
  arXiv  Detail & Related papers  (2025-05-05T06:11:12Z)
• GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning [35.429904556288996]
  We introduce GenPRM, a generative process reward model that performs explicit Chain-of-Thought (CoT) reasoning with code verification.<n> Experimental results show that GenPRM significantly outperforms prior PRMs with only 23K training data from MATH dataset.
  arXiv  Detail & Related papers  (2025-04-01T15:21:05Z)
• Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models [33.547353090281284]
  We propose a novel reward model approach called the Hierarchical Reward Model.<n>It evaluates both individual and consecutive reasoning steps at both fine-grained and coarse-grained levels.<n>It excels at assessing multi-step reasoning coherence, especially when flawed steps are later corrected through self-reflection.
  arXiv  Detail & Related papers  (2025-03-16T15:18:40Z)
• Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning [55.96599486604344]
  We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process. We use Monte Carlo Tree Search (MCTS) to iteratively collect preference data, utilizing its look-ahead ability to break down instance-level rewards into more granular step-level signals. The proposed algorithm employs Direct Preference Optimization (DPO) to update the LLM policy using this newly generated step-level preference data.
  arXiv  Detail & Related papers  (2024-05-01T11:10:24Z)
• Let's Reinforce Step by Step [10.65244642965387]
  We use Reinforcement Learning from Human Feedback to shape model reasoning processes. Our results show that the fine-grained reward provided by PRM-based methods enhances accuracy on simple mathematical reasoning. We also show the critical role reward aggregation functions play in model performance.
  arXiv  Detail & Related papers  (2023-11-10T01:35:51Z)
• Let's reward step by step: Step-Level reward model as the Navigators for Reasoning [64.27898739929734]
  Process-Supervised Reward Model (PRM) furnishes LLMs with step-by-step feedback during the training phase. We propose a greedy search algorithm that employs the step-level feedback from PRM to optimize the reasoning pathways explored by LLMs. To explore the versatility of our approach, we develop a novel method to automatically generate step-level reward dataset for coding tasks and observed similar improved performance in the code generation tasks.
  arXiv  Detail & Related papers  (2023-10-16T05:21:50Z)
• Model-Augmented Q-learning [112.86795579978802]
  We propose a MFRL framework that is augmented with the components of model-based RL. Specifically, we propose to estimate not only the $Q$-values but also both the transition and the reward with a shared network. We show that the proposed scheme, called Model-augmented $Q$-learning (MQL), obtains a policy-invariant solution which is identical to the solution obtained by learning with true reward.
  arXiv  Detail & Related papers  (2021-02-07T17:56:50Z)

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.