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

2025-10-01

AI Summary

Current large vision-language models (VLMs) perform near-randomly on fundamental perceptual reasoning tasks—such as jigsaw puzzle solving—revealing profound limitations in their multimodal understanding. To address this, we propose AGILE, the first framework that formulates jigsaw solving as a code-driven, interactive reinforcement learning process: an agent generates executable action code, receives fine-grained visual feedback, and dynamically updates its internal environment state, thereby closing the perception–reasoning–action loop. This paradigm mitigates key bottlenecks in multimodal RL—namely, data scarcity and poor scalability. Experiments demonstrate that AGILE boosts accuracy on 2×2 jigsaw puzzles from 9.5% to 82.8%, while achieving an average +3.1% improvement across nine general vision benchmarks, significantly enhancing out-of-distribution generalization.

Technology Category

• Computer Vision: Large Vision Models
• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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 $ imes$ 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 .

Problem

• Enhancing visual perception and reasoning in Vision-Language Models
• Addressing limited capabilities in multimodal understanding and reasoning
• Solving jigsaw tasks through interactive learning and feedback

Innovation

• AGILE uses interactive jigsaw solving for model learning
• Model generates executable code for environment actions
• Iterative feedback cycle enhances perception and reasoning