一种多智能体对话推荐系统
A Multi-Agent Conversational Recommender System
AI总结：
针对LLM用于对话推荐时对话流程难管控、用户反馈未被充分利用的问题，提出含多智能体行为规划框架和用户反馈感知反思机制的MACRS系统，实验证明其能提升用户交互体验。
摘要：
大语言模型（Large Language Models, LLMs）具备与用户开展流畅多轮对话的强大能力，有潜力进一步提升对话推荐系统（Conversational Recommender System, CRS）的性能。与LLM擅长的无目的闲聊不同，CRS有明确的目标，因此必须管控LLM中的对话流程，才能成功向用户推荐合适的物品。此外，CRS中的用户反馈可帮助系统更好地建模用户偏好，这一点却被现有研究忽略。然而，仅通过提示工程让LLM开展对话推荐，无法解决上述两大关键挑战。\n 本文提出多智能体对话推荐系统（Multi-Agent Conversational Recommender System, MACRS），该系统包含两个核心模块。首先，我们设计了一个多智能体行为规划框架，可基于4个以LLM为核心的智能体管控对话流程。该协作式多智能体框架会基于不同的对话行为生成多种候选回复，再从中选择最合适的回复作为系统回复，能够帮助MACRS规划恰当的对话行为。其次，我们提出一种感知用户反馈的反思机制，利用用户反馈推理前序轮次中出现的错误，以调整对话行为规划，并从隐式语义中挖掘更高层级的用户信息。我们基于用户模拟器开展了大量实验，以验证MACRS在推荐效果和用户偏好收集方面的有效性。实验结果表明，与直接使用LLMs相比，MACRS在用户交互体验上有所提升。
英文摘要：
Due to strong capabilities in conducting fluent, multi-turn conversations with users, Large Language Models (LLMs) have the potential to further improve the performance of Conversational Recommender System (CRS). Unlike the aimless chit-chat that LLM excels at, CRS has a clear target. So it is imperative to control the dialogue flow in the LLM to successfully recommend appropriate items to the users. Furthermore, user feedback in CRS can assist the system in better modeling user preferences, which has been ignored by existing studies. However, simply prompting LLM to conduct conversational recommendation cannot address the above two key challenges. In this paper, we propose Multi-Agent Conversational Recommender System (MACRS) which contains two essential modules. First, we design a multi-agent act planning framework, which can control the dialogue flow based on four LLM-based agents. This cooperative multi-agent framework will generate various candidate responses based on different dialogue acts and then choose the most appropriate response as the system response, which can help MACRS plan suitable dialogue acts. Second, we propose a user feedback-aware reflection mechanism which leverages user feedback to reason errors made in previous turns to adjust the dialogue act planning, and higher-level user information from implicit semantics. We conduct extensive experiments based on user simulator to demonstrate the effectiveness of MACRS in recommendation and user preferences collection. Experimental results illustrate that MACRS demonstrates an improvement in user interaction experience compared to directly using LLMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
