MuSEAgent: A Multimodal Reasoning Agent with Stateful Experiences
For multimodal agent research, this work addresses the bottleneck of leveraging past experiences for decision-making, offering a novel method that improves performance over existing trajectory-level approaches.
MuSEAgent introduces a stateful experience learning paradigm that abstracts interaction data into atomic decision experiences, outperforming trajectory-level retrieval baselines on visual perception and multimodal reasoning tasks.
Research agents have recently achieved significant progress in information seeking and synthesis across heterogeneous textual and visual sources. In this paper, we introduce MuSEAgent, a multimodal reasoning agent that enhances decision-making by extending the capabilities of research agents to discover and leverage stateful experiences. Rather than relying on trajectory-level retrieval, we propose a stateful experience learning paradigm that abstracts interaction data into atomic decision experiences through hindsight reasoning. These experiences are organized into a quality-filtered experience bank that supports policy-driven experience retrieval at inference time. Specifically, MuSEAgent enables adaptive experience exploitation through complementary wide- and deep-search strategies, allowing the agent to dynamically retrieve multimodal guidance across diverse compositional semantic viewpoints. Extensive experiments demonstrate that MuSEAgent consistently outperforms strong trajectory-level experience retrieval baselines on both fine-grained visual perception and complex multimodal reasoning tasks. These results validate the effectiveness of stateful experience modeling in improving multimodal agent reasoning.