CAPO: Towards Enhancing LLM Reasoning through Verifiable Generative Credit Assignment

• URL: http://arxiv.org/abs/2508.02298v1
• Date: Mon, 04 Aug 2025 11:06:08 GMT
• Title: CAPO: Towards Enhancing LLM Reasoning through Verifiable Generative Credit Assignment
• Authors: Guofu Xie, Yunsheng Shi, Hongtao Tian, Ting Yao, Xiao Zhang,
• Abstract summary: Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback.<n>Current RLVR methods treat whole responses as single actions, assigning the same reward to every token.<n>This coarse-grained feedback hampers precise credit assignment, making it hard for models to identify which reasoning steps lead to success or failure.
• Score: 39.965170904699974
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback, helping to mitigate reward hacking. However, current RLVR methods typically treat whole responses as single actions, assigning the same reward to every token. This coarse-grained feedback hampers precise credit assignment, making it hard for models to identify which reasoning steps lead to success or failure, and often results in suboptimal policies and inefficient learning. Methods like PPO provide credit assignment through value estimation, but often yield inaccurate and unverifiable signals due to limited sampling. On the other hand, methods using Process Reward Models can provide step-by-step judgments for each reasoning step, but they require high-quality process supervision labels and are time-consuming when applied in online reinforcement learning (RL). To overcome these limitations, we introduce a simple but efficient method Credit Assignment Policy Optimization (CAPO). Given a reasoning response rollout from the policy model, CAPO directly leverages an off-the-shelf, general-purpose LLM as a Generative Process Reward Model (LLM-as-GenPRM) to generate all step-wise critique by one pass, thereby providing verifiable token-level rewards to refine the tokens that were originally assigned identical rule-based rewards. This enables more fine-grained credit assignment in an effective way. Furthermore, to enhance the accuracy and robustness of CAPO, we employ voting mechanisms that scale with the number of generated critiques. Extensive experiments using different backbones like Llama and Qwen models and in different sizes show that CAPO consistently outperforms supervised learning-based and RL-based fine-tuning methods across six challenging mathematical benchmarks and three out-of-domain benchmarks.

Related papers

• Revisiting LLM Reasoning via Information Bottleneck [57.519119962528166]
  Large language models (LLMs) have recently demonstrated remarkable progress in reasoning capabilities through reinforcement learning with verifiable rewards (RLVR)<n>We present a theoretical characterization of LLM reasoning grounded in information bottleneck (IB) principle.<n>We propose IB-aware reasoning optimization (IBRO), a framework that encourages reasoning trajectories to be both informative about the final correct answer and generalizable.
  arXiv  Detail & Related papers  (2025-07-24T13:14:25Z)
• RLPR: Extrapolating RLVR to General Domains without Verifiers [103.14103272635893]
  We propose RLPR, a simple verifier-free framework that extrapolates RLVR to broader general domains.<n>We find that addressing the high variance of this noisy probability reward is crucial to make it work.<n>RLPR consistently improves reasoning capabilities in both areas for Gemma, Llama, and Qwen based models.
  arXiv  Detail & Related papers  (2025-06-23T02:56:36Z)
• RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling [25.12721060984898]
  Rule-based reasoning has been acknowledged as one of the fundamental problems in reasoning.<n>We introduce Reinforced Rule-based Reasoning, a.k.a. RuleReasoner, a simple yet effective method to conduct rule-based reasoning.<n>Specifically, RuleReasoner resamples each training batch by updating the sampling weights of different domains based on historical rewards.
  arXiv  Detail & Related papers  (2025-06-10T10:31:21Z)
• Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective [6.069069082518759]
  We study the Zero-Reward Assumption in reinforcement learning for large language models (LLMs)<n>We show that the policy gradient based on true, unknown token-level rewards can be unbiasedly estimated using only a response-level reward model.<n>We propose a new algorithm: Token-Reinforced Policy Optimization (TRePO)
  arXiv  Detail & Related papers  (2025-06-03T07:44:31Z)
• Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable Rewards [11.149294285483782]
  We propose a unified RLVR-based training paradigm that bridges the gap between non-verifiable tasks and verifiable rewards.<n>We introduce a writing-principle-based pairwise Generative Reward Model (GenRM) and a novel Bootstrapped Relative Policy Optimization (BRPO) algorithm.<n>Our approach empowers LLMs to develop robust writing capabilities without supervised fine-tuning.
  arXiv  Detail & Related papers  (2025-05-30T14:34:57Z)
• Discriminative Policy Optimization for Token-Level Reward Models [55.98642069903191]
  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.
  arXiv  Detail & Related papers  (2025-05-29T11:40:34Z)
• Scalable Best-of-N Selection for Large Language Models via Self-Certainty [65.31658824274894]
  Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models.<n>We propose self-certainty, a novel and efficient metric to estimate response quality without requiring external reward models.<n>Our findings establish self-certainty as a practical and efficient way for improving LLM reasoning capabilities.
  arXiv  Detail & Related papers  (2025-02-25T19:08:07Z)
• VinePPO: Refining Credit Assignment in RL Training of LLMs [66.80143024475635]
  We propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates.<n>Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL [14.091146805312636]
  Credit assignment problem is a central challenge in Reinforcement Learning (RL) Credit Assignment with Language Models (CALM) is a novel approach to automate credit assignment via reward shaping and options discovery. Preliminary results indicate that the knowledge of Large Language Models is a promising prior for credit assignment in RL.
  arXiv  Detail & Related papers  (2024-09-19T14:08:09Z)

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.