Search papers, labs, and topics across Lattice.
This paper introduces MMEACR, a Multimodal Memory-Enhanced Agent Collaboration framework designed to enhance recommendation systems by integrating visual evidence and user preferences through a dual-track memory architecture. The framework separates reasoning and matching processes, allowing for persistent multimodal memories and fine-grained matching that captures detailed cross-modal signals. Experimental results demonstrate that MMEACR outperforms existing LLM-based and agent-based approaches, particularly in scenarios requiring visual grounding, highlighting its effectiveness in addressing the limitations of traditional text-centric models.
MMEACR achieves significant performance improvements in visually grounded recommendations by effectively integrating multimodal memory and collaborative reasoning.
Large language model (LLM)-based agentic recommender systems show promise in modeling user preferences through natural-language reasoning, yet they remain limited by text-centric inputs and coarse-grained memory updates, making agents prone to missing visual evidence, semantic noise, and preference drift. To address these limitations, we propose MMEACR, a Multimodal Memory-Enhanced Agent Collaboration framework for recommendation. MMEACR introduces a dual-track memory architecture that separates interpretable agent reasoning from fine-grained multimodal matching. In the reasoning track, collaborative User and Item Memory Agents maintain persistent multimodal memories and update them through an attribute-guided reinforcement-and-reflection mechanism. In the matching track, a decoupled multi-modal embedding memory is built from raw interaction narratives and item images to preserve detailed cross-modal signals beyond structured memory updates. The two tracks are integrated through weighted Reciprocal Rank Fusion to produce robust and interpretable rankings. Experiments on three real-world domains show that MMEACR achieves strong overall performance against competitive LLM-based and agent-based baselines, with notable gains in visually grounded recommendation scenarios.
