Saved in:
Bibliographic Details
Main Authors: Wang, Shijian, Jin, Jiarui, Fu, Runhao, Yan, Zexuan, Wang, Xingjian, Hu, Mengkang, Wang, Eric, Li, Xiaoxi, Zhang, Kangning, Yao, Li, Jiao, Wenxiang, Cheng, Xuelian, Lu, Yuan, Ge, Zongyuan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.27813
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.