MACRec: a Multi-Agent Collaboration Framework for Recommendation (2402.15235v3)
Abstract: LLM-based agents have gained considerable attention for their decision-making skills and ability to handle complex tasks. Recognizing the current gap in leveraging agent capabilities for multi-agent collaboration in recommendation systems, we introduce MACRec, a novel framework designed to enhance recommendation systems through multi-agent collaboration. Unlike existing work on using agents for user/item simulation, we aim to deploy multi-agents to tackle recommendation tasks directly. In our framework, recommendation tasks are addressed through the collaborative efforts of various specialized agents, including Manager, User/Item Analyst, Reflector, Searcher, and Task Interpreter, with different working flows. Furthermore, we provide application examples of how developers can easily use MACRec on various recommendation tasks, including rating prediction, sequential recommendation, conversational recommendation, and explanation generation of recommendation results. The framework and demonstration video are publicly available at https://github.com/wzf2000/MACRec.
- Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877–1901.
- Trends in distributed artificial intelligence. Artificial Intelligence Review 6 (1992), 35–66.
- Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors in agents. arXiv preprint arXiv:2308.10848 (2023).
- Improving Factuality and Reasoning in Language Models through Multiagent Debate. arXiv preprint arXiv:2305.14325 (2023).
- Recommender ai agent: Integrating large language models for interactive recommendations. arXiv preprint arXiv:2308.16505 (2023).
- Camel: Communicative agents for” mind” exploration of large scale language model society. arXiv preprint arXiv:2303.17760 (2023).
- Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332 (2021).
- GPT-in-the-Loop: Adaptive Decision-Making for Multiagent Systems. arXiv preprint arXiv:2308.10435 (2023).
- OpenAI. 2023. GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2023).
- Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface. arXiv preprint arXiv:2303.17580 (2023).
- RAH! RecSys-Assistant-Human: A Human-Central Recommendation Framework with Large Language Models. arXiv preprint arXiv:2308.09904 (2023).
- Peter Stone and Manuela Veloso. 2000. Multiagent systems: A survey from a machine learning perspective. Autonomous Robots 8 (2000), 345–383.
- Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023).
- Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575, 7782 (2019), 350–354.
- When Large Language Model based Agent Meets User Behavior Analysis: A Novel User Simulation Paradigm. arXiv preprint ArXiv:2306.02552 (2023).
- Recmind: Large language model powered agent for recommendation. arXiv preprint arXiv:2308.14296 (2023).
- Michael Wooldridge and Nicholas R Jennings. 1995. Intelligent agents: Theory and practice. The knowledge engineering review 10, 2 (1995), 115–152.
- Autogen: Enabling next-gen llm applications via multi-agent conversation framework. arXiv preprint arXiv:2308.08155 (2023).
- React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629 (2022).
- Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414 (2022).
- On generative agents in recommendation. arXiv preprint arXiv:2310.10108 (2023).
- Building cooperative embodied agents modularly with large language models. arXiv preprint arXiv:2307.02485 (2023).
- Agentcf: Collaborative learning with autonomous language agents for recommender systems. arXiv preprint arXiv:2310.09233 (2023).