Multi-Agent Collaborative Filtering: Orchestrating Users and Items for Agentic Recommendations

TL;DR

This paper introduces MACF, a multi-agent collaborative filtering framework using LLM agents to improve agentic recommendations by dynamically orchestrating user and item agents for better collaboration and personalization.

Contribution

The paper proposes a novel MACF framework that leverages multi-agent collaboration and dynamic orchestration to enhance agentic recommendation systems, addressing limitations of static preference aggregation.

Findings

MACF outperforms strong baselines on multiple datasets.

Dynamic agent recruitment improves recommendation quality.

Orchestrated multi-agent collaboration enhances personalization.

Abstract

Agentic recommendations cast recommenders as large language model (LLM) agents that can plan, reason, use tools, and interact with users of varying preferences in web applications. However, most existing agentic recommender systems focus on generic single-agent plan-execute workflows or multi-agent task decomposition pipelines. Without recommendation-oriented design, they often underuse the collaborative signals in the user-item interaction history, leading to unsatisfying recommendation results. To address this, we propose the Multi-Agent Collaborative Filtering (MACF) framework for agentic recommendations, drawing an analogy between traditional collaborative filtering algorithms and LLM-based multi-agent collaboration. Specifically, given a target user and query, we instantiate similar users and relevant items as LLM agents with unique profiles. Each agent is able to call retrieval tools, suggest candidate items, and interact with other agents. Different from the static preference aggregation in traditional collaborative filtering, MACF employs a central orchestrator agent to adaptively manage the collaboration between user and item agents via dynamic agent recruitment and personalized collaboration instruction. Experimental results on datasets from three different domains show the advantages of our MACF framework compared to strong agentic recommendation baselines.