MuSEAgent: A Multimodal Reasoning Agent with Stateful Experiences

• URL: http://arxiv.org/abs/2603.27813v1
• Date: Sun, 29 Mar 2026 18:54:31 GMT
• Title: MuSEAgent: A Multimodal Reasoning Agent with Stateful Experiences
• Abstract summary: We introduce MuSEAgent, a multimodal reasoning agent that enhances decision-making by extending the capabilities of research agents to discover and leverage stateful experiences.<n>Experiments demonstrate that MuSEAgent consistently outperforms strong trajectory-level experience retrieval baselines on both fine-grained visual perception and complex multimodal reasoning tasks.
• Score: 39.79876767762482
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Learning Agent-Compatible Context Management for Long-Horizon Tasks [79.09330817637205]
  We introduce Adaptive Context Management (AdaCoM), which trains an external LLM to manage the context of a frozen agent.<n>AdaCoM substantially improves performance by preserving task constraints and progress while pruning stale content.<n>The learned strategies reveal a Fidelity-Reliability Trade-off: agents with higher vanilla ReAct performance benefit from higher-fidelity context preservation, whereas lower-performing agents require more aggressive compression to stay within a reliable reasoning regime.
  arXiv  Detail & Related papers  (2026-05-29T03:21:08Z)
• Rethinking Experience Utilization in Self-Evolving Language Model Agents [51.10420305280499]
  Self-evolving agents improve by accumulating and reusing experience from past interactions.<n>This paper studies experience utilization as a critical design dimension of self-evolving agents.
  arXiv  Detail & Related papers  (2026-05-08T02:48:49Z)
• Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic Search [5.481048072631037]
  We propose a novel framework, Hierarchical Experience (HiExp), to enhance the performance and training of search agents.<n>We extract empirical knowledge through contrastive analysis and a multi-level clustering mechanism, transforming raw reasoning trajectories into hierarchical experience knowledge.<n>Our approach achieves substantial performance gains and also exhibits strong cross-task and cross-algorithm generalization.
  arXiv  Detail & Related papers  (2026-04-09T11:44:44Z)
• Learning to Retrieve from Agent Trajectories [72.8923565916533]
  We argue that retrieval models for agentic search should be trained directly from agent interaction data.<n>We introduce learning to retrieve from agent trajectories as a new training paradigm, where supervision is derived from multi-step agent interactions.<n>Our results highlight agent trajectories as a practical and scalable supervision source, pointing to a promising direction for retrieval in the era of agentic search.
  arXiv  Detail & Related papers  (2026-03-30T17:59:02Z)
• Retrieval-Augmented LLM Agents: Learning to Learn from Experience [16.248836438253814]
  We study how to train retrieval-augmented LLM agents to leverage retrieved trajectories in-context.<n>We establish a robust supervised fine-tuning (SFT) recipe using LoRA that outperforms several state-of-the-art agent training pipelines.<n>Our results demonstrate that this combined approach significantly improves generalization to unseen tasks.
  arXiv  Detail & Related papers  (2026-03-18T20:45:04Z)
• Agent Learning via Early Experience [93.83579011718858]
  A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks.<n>Most current agents rely on supervised fine-tuning on expert data, which is challenging to scale and generalizes poorly.<n>We study two strategies of using such data: (1) Implicit world modeling, which uses collected states to ground the policy in environment dynamics; and (2) Self-reflection, where the agent learns from its suboptimal actions to improve reasoning and decision-making.
  arXiv  Detail & Related papers  (2025-10-09T17:59:17Z)
• Literature Review Of Multi-Agent Debate For Problem-Solving [0.0]
  Multi-agent large language models (MA-LLMs) are a rapidly growing research area that leverages multiple interacting language agents to tackle complex tasks.<n>This literature review synthesizes the latest research on agent profiles, communication structures, and decision-making processes.
  arXiv  Detail & Related papers  (2025-05-29T13:57:00Z)
• Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration [63.90193684394165]
  We introduce multi-agent cross-task experiential learning (MAEL), a novel framework that endows LLM-driven agents with explicit cross-task learning and experience accumulation.<n>During the experiential learning phase, we quantify the quality for each step in the task-solving workflow and store the resulting rewards.<n>During inference, agents retrieve high-reward, task-relevant experiences as few-shot examples to enhance the effectiveness of each reasoning step.
  arXiv  Detail & Related papers  (2025-05-29T07:24:37Z)
• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process.<n>We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing [70.25689961697523]
  We propose a generalizable algorithm that enhances sequential reasoning by cross-task experience sharing and selection. Our work bridges the gap between existing sequential reasoning paradigms and validates the effectiveness of leveraging cross-task experiences.
  arXiv  Detail & Related papers  (2024-10-22T03:59:53Z)
• Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks [44.42989163847349]
  Large Language Models (LLMs) have led to significant breakthroughs in various natural language processing tasks.<n> generating factually consistent responses in knowledge-intensive scenarios remains a challenge.<n>This paper introduces SMART, a novel multi-agent framework that leverages external knowledge to enhance the interpretability and factual consistency of LLM-generated responses.
  arXiv  Detail & Related papers  (2024-07-13T13:58:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.