MuSEAgent: A Multimodal Reasoning Agent with Stateful Experiences

TL;DR

MuSEAgent is a multimodal reasoning agent that uses a novel stateful experience learning paradigm to improve decision-making across visual and textual sources, outperforming existing retrieval methods.

Contribution

It introduces a stateful experience learning framework with a quality-filtered experience bank for adaptive multimodal reasoning, advancing beyond trajectory-level retrieval.

Findings

MuSEAgent outperforms trajectory-level experience retrieval baselines.

The approach improves performance on fine-grained visual perception tasks.

The method enhances complex multimodal reasoning capabilities.

Abstract

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.