arXiv cs.AI· Ziqi Miao, Haonan Jia, Lijun Li, Chen Qian, Yuan Xiong, Wenting Yan, Yongyao Wang, Zaoying Huang, Ken Deng, Jing Shao·· 4 小时前AI 评分34
PRCO:面向多模态推理的感知-推理协同进化框架
Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning
AI 导读
PRCO 是一个双角色 RLVR 框架,用共享策略让 Observer 生成针对问题的证据描述、Solver 基于该描述给出最终答案,并分别施加可验证结果奖励与下游效用奖励。在八个多模态推理基准上,PRCO 相比基座模型平均准确率提升超过 7 分,优于此前的开源 RL 微调基线。
正文 · 原文
Abstract:Reinforcement learning with verifiable rewards (RLVR) has substantially enhanced the reasoning capabilities of multimodal large language models (MLLMs). However, existing RLVR approaches typically rely on outcome-driven optimization that updates both perception and reasoning using a shared reward based solely on the final answer. This shared reward blurs credit assignment, frequently improving reasoning patterns while failing to reliably enhance the accuracy of upstream visual evidence extraction. To address this perception bottleneck, we introduce PRCO (Perception-Reasoning Coevolution), a dual-role RLVR framework with a shared policy. PRCO consists of two cooperative roles: an Observer that generates an evidence caption tailored to the question and a Solver that predicts the final answer based on this caption. Crucially, PRCO employs role-specific reward signals: the Solver is optimized using verifiable outcome rewards on the final answer, while the Observer receives a utility reward derived from the Solver's downstream success. Extensive experiments across eight challenging multimodal reasoning benchmarks demonstrate that PRCO yields consistent improvements across model scales by over 7 points on average accuracy compared to the base model, outperforming prior open-source RL-tuned baselines.
| Comments: | 21 pages, 15 figures, 6 tables |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2603.28618 [cs.AI] |
| (or arXiv:2603.28618v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2603.28618 arXiv-issued DOI via DataCite |
|
| Journal reference: | EMNLP 2026 |
Submission history
From: Miao Ziqi [view email]
[v1]
Mon, 30 Mar 2026 16:03:56 UTC (2,178 KB)
[v2]
Thu, 9 Apr 2026 14:15:05 UTC (2,177 KB)
[v3]
Tue, 17 Nov 2026 12:57:34 UTC (2,175 KB)
来源:arXiv cs.AI · arxiv.org