Perception-Aware Policy Optimization for Multimodal Reasoning

• URL: http://arxiv.org/abs/2507.06448v4
• Date: Thu, 07 Aug 2025 04:33:56 GMT
• Title: Perception-Aware Policy Optimization for Multimodal Reasoning
• Authors: Zhenhailong Wang, Xuehang Guo, Sofia Stoica, Haiyang Xu, Hongru Wang, Hyeonjeong Ha, Xiusi Chen, Yangyi Chen, Ming Yan, Fei Huang, Heng Ji,
• Abstract summary: A major source of error in current multimodal reasoning lies in the perception of visual inputs.<n>We propose PAPO, a novel policy gradient algorithm that encourages the model to learn to perceive while learning to reason.<n>We observe a substantial reduction of 30.5% in perception errors, indicating improved perceptual capabilities with PAPO.
• Score: 79.56070395437898
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has proven to be a highly effective strategy for endowing Large Language Models (LLMs) with robust multi-step reasoning abilities. However, its design and optimizations remain tailored to purely textual domains, resulting in suboptimal performance when applied to multimodal reasoning tasks. In particular, we observe that a major source of error in current multimodal reasoning lies in the perception of visual inputs. To address this bottleneck, we propose PAPO, a novel policy gradient algorithm that encourages the model to learn to perceive while learning to reason. Specifically, we introduce the Implicit Perception Loss in the form of a KL divergence term, which can be seamlessly plugged into mainstream RLVR algorithms such as GRPO and DAPO. Notably, PAPO does not rely on additional data curation, reward models, or stronger teacher models. To further enhance the training stability of PAPO, we introduce the Double Entropy Loss, which effectively regularizes the new KL objective without compromising performance. Despite its simplicity, PAPO yields significant overall improvements of 4.4%-17.5% on diverse multimodal benchmarks. The improvements are more pronounced, approaching 8.0%-19.1%, on tasks with high vision dependency. We also observe a substantial reduction of 30.5% in perception errors, indicating improved perceptual capabilities with PAPO. Overall, our work introduces a deeper integration of perception-aware supervision into core learning objectives and lays the groundwork for a new RL framework that encourages visually grounded reasoning. Code and data will be made publicly available for research purposes. Project page: https://mikewangwzhl.github.io/PAPO.

Related papers

• ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding [71.654781631463]
  ReAgent-V is a novel agentic video understanding framework.<n>It integrates efficient frame selection with real-time reward generation during inference.<n>Extensive experiments on 12 datasets demonstrate significant gains in generalization and reasoning.
  arXiv  Detail & Related papers  (2025-06-02T04:23:21Z)
• Reinforcing Video Reasoning with Focused Thinking [65.85683941058916]
  We propose TW-GRPO, a novel framework that enhances visual reasoning with focused thinking and dense reward granularity.<n>Specifically, we employ a token weighting mechanism that prioritizes tokens with high informational density.<n>We also reformulate RL training by shifting from single-choice to multi-choice QA tasks.
  arXiv  Detail & Related papers  (2025-05-30T15:42:19Z)
• On-Policy RL with Optimal Reward Baseline [109.47676554514193]
  On-Policy RL with Optimal reward baseline (OPO) is a novel and simplified reinforcement learning algorithm.<n>OPO emphasizes the importance of exact on-policy training, which empirically stabilizes the training process and enhances exploration.<n>Results demonstrate OPO's superior performance and training stability without additional models or regularization terms.
  arXiv  Detail & Related papers  (2025-05-29T15:58:04Z)
• AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization [11.381262184752234]
  We propose AdPO, a novel adversarial defense strategy for LVLMs based on preference optimization.<n>For the first time, we reframe adversarial training as a preference optimization problem, aiming to enhance the model's preference for generating normal outputs on clean inputs.<n>We validate that training on smaller LVLMs can achieve competitive performance while maintaining efficiency comparable to baseline methods.
  arXiv  Detail & Related papers  (2025-04-02T13:43:21Z)
• Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation [29.579349371114702]
  Direct Preference Optimization (DPO) is a cost-effective alternative to reinforcement learning (RL) for large language models (LLMs)<n>We show that a single round of DPO with coarse filtering significantly enhances mathematical reasoning performance.<n>With simple verifiable rewards, our model achieves RL-level performance with significantly lower computational overhead.
  arXiv  Detail & Related papers  (2025-03-17T06:28:25Z)
• 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)
• 3D-Properties: Identifying Challenges in DPO and Charting a Path Forward [17.27880657597116]
  We revisit DPO, analyzing its theoretical foundations and empirical performance.<n>We identify three key properties, termed 3D properties, that emerge from DPO's learning process.<n>We propose simple regularization techniques that improve training stability and performance.
  arXiv  Detail & Related papers  (2024-06-11T14:59:24Z)
• REBEL: Reinforcement Learning via Regressing Relative Rewards [59.68420022466047]
  We propose REBEL, a minimalist RL algorithm for the era of generative models.<n>In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL.<n>We find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO.
  arXiv  Detail & Related papers  (2024-04-25T17:20:45Z)
• PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models [13.313186665410486]
  Reward finetuning has emerged as a promising approach to aligning foundation models with downstream objectives. Existing reward finetuning methods are limited by their instability in large-scale prompt datasets. We propose Proximal Reward Difference Prediction (PRDP) to enable stable black-box reward finetuning for diffusion models.
  arXiv  Detail & Related papers  (2024-02-13T18:58:16Z)
• Secrets of RLHF in Large Language Models Part I: PPO [81.01936993929127]
  Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. reinforcement learning with human feedback (RLHF) emerges as the pivotal technological paradigm underpinning this pursuit. In this report, we dissect the framework of RLHF, re-evaluate the inner workings of PPO, and explore how the parts comprising PPO algorithms impact policy agent training.
  arXiv  Detail & Related papers  (2023-07-11T01:55:24Z)
• Fine-Tuning Language Models with Advantage-Induced Policy Alignment [80.96507425217472]
  We propose a novel algorithm for aligning large language models to human preferences. We show that it consistently outperforms PPO in language tasks by a large margin. We also provide a theoretical justification supporting the design of our loss function.
  arXiv  Detail & Related papers  (2023-06-04T01:59:40Z)

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.