面向视觉语言模型的自主拼图交互学习：提升视觉感知与推理能力

Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models

October 1, 2025

作者: Yu Zeng, Wenxuan Huang, Shiting Huang, Xikun Bao, Yukun Qi, Yiming Zhao, Qiuchen Wang, Lin Chen, Zehui Chen, Huaian Chen, Wanli Ouyang, Feng Zhao

cs.AI

摘要

尽管当前的大型视觉-语言模型（VLMs）在多模态理解和推理方面取得了进展，但其基本的感知和推理能力仍显不足。具体而言，即使在简单的拼图任务上，现有VLMs的表现也近乎随机，揭示了其在核心感知和推理能力上的缺陷。虽然高质量的视觉-语言数据能够提升这些能力，但其稀缺性和有限的可扩展性带来了显著的限制。为解决这一问题，我们提出了AGILE，即一种用于增强VLMs视觉感知和推理能力的交互式拼图学习代理。AGILE将拼图解决过程构建为一个交互式流程，使模型能够逐步与环境互动。在每一步中，模型根据当前状态生成可执行代码以执行动作，而环境则提供细粒度的视觉反馈以指导任务完成。通过这种观察与交互的迭代循环，模型通过探索和反馈逐步提升其感知和推理能力。实验结果表明，AGILE不仅在复杂度各异的拼图任务上大幅提升了性能（例如，在2×2设置下将准确率从9.5%提升至82.8%），还在9项通用视觉任务上展现出强大的泛化能力，平均提升了3.1%。这些结果标志着感知和推理能力的显著增强。本工作为推进多模态模型的推理和泛化能力开辟了新途径，并为多模态强化学习数据的稀缺性提供了一个高效、可扩展的解决方案。代码和数据集可在https://github.com/yuzeng0-0/AGILE 获取。

English

Although current large Vision-Language Models (VLMs) have advanced in multimodal understanding and reasoning, their fundamental perceptual and reasoning abilities remain limited. Specifically, even on simple jigsaw tasks, existing VLMs perform near randomly, revealing deficiencies in core perception and reasoning capabilities. While high-quality vision-language data can enhance these capabilities, its scarcity and limited scalability impose significant constraints. To address this, we propose AGILE, an Agentic jiGsaw Interaction Learning for Enhancing visual perception and reasoning in VLMs. AGILE formulates jigsaw solving as an interactive process, enabling the model to progressively engage with the environment. At each step, the model generates executable code to perform an action based on the current state, while the environment provides fine-grained visual feedback to guide task completion. Through this iterative cycle of observation and interaction, the model incrementally improves its perceptual and reasoning capabilities via exploration and feedback. Experimental results show that AGILE not only substantially boosts performance on jigsaw tasks of varying complexity (e.g., increasing accuracy from 9.5% to 82.8% under the 2 times 2 setting) but also demonstrates strong generalization across 9 general vision tasks, achieving an average improvement of 3.1%. These results indicate notable enhancements in both perceptual and reasoning abilities. This work opens a new avenue for advancing reasoning and generalization in multimodal models and provides an efficient, scalable solution to the scarcity of multimodal reinforcement learning data. The code and datasets is available at https://github.com/yuzeng0-0/AGILE .