Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization

• URL: http://arxiv.org/abs/2605.29198v2
• Date: Fri, 29 May 2026 15:12:05 GMT
• Title: Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization
• Abstract summary: Group-advantage-based reinforcement learning methods, such as GRPO and DAPO, have demonstrated strong performance across diverse domains.<n>We propose Guidance Contrastive Policy Optimization (GCPO), a novel algorithm that enables per-token credit assignment by contrasting model predictions under positive and negative prompts.<n>GCPO consistently outperforms GRPO and DAPO baselines on both text-to-image generation and chain-of-thought reasoning benchmarks.
• Score: 41.15412049767388
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Group-advantage-based reinforcement learning methods, such as GRPO and DAPO, have demonstrated strong performance across diverse domains, including mathematical reasoning and text-to-image generation. However, their reliance on sample-level rewards introduces a key limitation as uniform credit assignment across all tokens fails to capture fine-grained, token-level contributions. To address this issue, we propose Guidance Contrastive Policy Optimization (GCPO), a novel algorithm that enables per-token credit assignment by contrasting model predictions under positive and negative prompts. Rather than uniformly broadcasting sample-level advantages, GCPO assigns token-level advantages proportional to the difference between these contrastive predictions, allowing more precise and informative learning signals. Empirically, we find that GCPO emphasizes semantically relevant regions such as visual areas aligned with textual prompts in text-to-image generation, and critical keywords within reasoning traces for chain-of-thought tasks. Through extensive experiments, GCPO consistently outperforms GRPO and DAPO baselines on both text-to-image generation and chain-of-thought reasoning benchmarks, demonstrating its effectiveness as a general and scalable optimization strategy for discrete policy learning.

Related papers

• Segment-Aligned Policy Optimization for Multi-Modal Reasoning [55.29606572822562]
  We propose a novel reinforcement learning paradigm that treats coherent reasoning steps, rather than tokens or full sequences as fundamental units of policy update.<n>Experiments on representative reasoning benchmarks demonstrate that SAPO consistently outperforms token-level and sequence-level policy optimization methods.<n>Our work underscores the importance of aligning reinforcement learning updates with the structure of reasoning, paving the way for more efficient and semantically grounded policy optimization in complex reasoning tasks.
  arXiv  Detail & Related papers  (2026-05-02T08:47:45Z)
• Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models [38.47027398567909]
  Perception-Grounded Policy Optimization (PGPO) is a novel fine-grained credit assignment framework that dynamically reshapes advantages at the token level.<n>We show that PGPO actively amplifies learning signals for visually-dependent tokens while suppressing gradient noise from linguistic priors.<n>Both theoretical and empirical analyses confirm that PGPO effectively reduces gradient variance, prevents training collapse, and acts as a potent regularizer for robust, perception-grounded multimodal reasoning.
  arXiv  Detail & Related papers  (2026-04-02T09:53:20Z)
• Owen-Shapley Policy Optimization (OSPO): A Principled RL Algorithm for Generative Search LLMs [12.75200353208858]
  Owen-Shapley Policy Optimization (OSPO) is a framework that redistributes sequence-level advantages based on tokens' marginal contributions to outcomes.<n>Unlike value-model-based methods requiring additional computation, OSPO employs potential-based reward shaping via Shapley-Owen attributions to assign segment-level credit.<n> Experiments on Amazon ESCI and H&M Fashion datasets show consistent gains over baselines.
  arXiv  Detail & Related papers  (2026-01-13T10:17:46Z)
• Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning [60.00161035836637]
  Group Relative Policy Optimization has emerged as a promising critic-free reinforcement learning paradigm for reasoning tasks.<n>We introduce Outcome-grounded Advantage Reshaping (OAR), a fine-grained credit assignment mechanism that redistributes advantages based on how much each token influences the model's final answer.<n>OAR-G achieves comparable gains with negligible computational overhead, both significantly outperforming a strong GRPO baseline.
  arXiv  Detail & Related papers  (2026-01-12T10:48:02Z)
• Latent Chain-of-Thought for Visual Reasoning [53.541579327424046]
  Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs)<n>We reformulate reasoning in LVLMs as posterior inference and propose a scalable training algorithm based on amortized variational inference.<n>We empirically demonstrate that the proposed method enhances the state-of-the-art LVLMs on seven reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-10-27T23:10:06Z)
• Perception-Consistency Multimodal Large Language Models Reasoning via Caption-Regularized Policy Optimization [72.30168853571216]
  multimodal large language models excel at tasks that integrate visual perception with symbolic reasoning.<n>CapPO integrates two key mechanisms: (1) a caption-based consistency regularization, which minimizes the divergence between responses conditioned on raw images and those conditioned on captions, and (2) a KL-weighted advantage estimation scheme, which adaptively scales reinforcement signals to strengthen perceptually consistent trajectories.
  arXiv  Detail & Related papers  (2025-09-26T04:32:26Z)
• Preserving Clusters in Prompt Learning for Unsupervised Domain Adaptation [29.809079908218607]
  This work introduces a fresh solution to reinforce base pseudo-labels and facilitate target-prompt learning.<n>We first propose to leverage the reference predictions based on the relationship between source and target visual embeddings.<n>We later show that there is a strong clustering behavior observed between visual and text embeddings in pre-trained multi-modal models.
  arXiv  Detail & Related papers  (2025-06-13T06:33:27Z)
• Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation [59.37587762543934]
  This paper studies the problem of weakly open-vocabulary semantic segmentation (WOVSS) Existing methods suffer from a granularity inconsistency regarding the usage of group tokens. We propose the prototypical guidance network (PGSeg) that incorporates multi-modal regularization.
  arXiv  Detail & Related papers  (2023-10-29T13:18:00Z)

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.