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

arXiv: https://arxiv.org/abs/2511.18413 · HTML: https://mlsanity.com/paper/2511.18413/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 23 Nov 2025.

## Placed in

- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)

## Builds on (most cited first, 12 of 12)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations](https://mlsanity.com/paper/2308.16505/) (2023)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems](https://mlsanity.com/paper/2310.09233/) (2023)
- [MACRec: a Multi-Agent Collaboration Framework for Recommendation](https://mlsanity.com/paper/2402.15235/) (2024)
- [A Multi-Agent Conversational Recommender System](https://mlsanity.com/paper/2402.01135/) (2024)
- [From Selection to Generation: A Survey of LLM-based Active Learning](https://mlsanity.com/paper/2502.11767/) (2025)
- [Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent](https://mlsanity.com/paper/2506.23485/) (2025)
- [SAND: Boosting LLM Agents with Self-Taught Action Deliberation](https://mlsanity.com/paper/2507.07441/) (2025)
- [Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards](https://mlsanity.com/paper/2510.01167/) (2025)

## Built on by (most cited first, 10 of 10)

- [Internalizing Multi-Agent Reasoning for Accurate and Efficient LLM-based Recommendation](https://mlsanity.com/paper/2602.09829/) (2026)
- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)
- [ProductResearch: Training E-Commerce Deep Research Agents via Multi-Agent Synthetic Trajectory Distillation](https://mlsanity.com/paper/2602.23716/) (2026)
- [AgenticTagger: Structured Item Representation for Recommendation with LLM Agents](https://mlsanity.com/paper/2602.05945/) (2026)
- [Self-Distilled Reinforcement Learning for Co-Evolving Agentic Recommender Systems](https://mlsanity.com/paper/2604.10029/) (2026)
- [How Personal Characteristics Shape User Exploration of Diverse Movie Recommendations with a LLM-Based Multi-Agent System](https://mlsanity.com/paper/2604.24405/) (2026)
- [Can We Steer the Black-Box? Towards Controllability-Centric Evaluation of Recommender Systems with Collaborative Agents](https://mlsanity.com/paper/2607.13418/) (2026)
- [Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivity](https://mlsanity.com/paper/2608.03272/) (2026)
- [Personalized Communication Skills for Agentic Recommender Systems](https://mlsanity.com/paper/2608.08417/) (2026)
- [ReMem: Rethinking Perception and Memory in Long-Context Recommendation Agents](https://mlsanity.com/paper/2609.37311/) (2026)

## Abstract (arXiv)

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.