arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.01609cs.AI
收藏

AgentRec:具备自适应智能的下一代基于大语言模型的多智能体协同推荐系统

AgentRec: Next-Generation LLM-Powered Multi-Agent Collaborative Recommendation with Adaptive Intelligence

Department of Software \& Microelectronics Peking University Beijing, China;Department of Software \& Microelectronics Peking University Beijing, China hangli\;Department of Software \& Microelectronics Peking University Beijing, China zehua\;Department of Software \& Microelectronics Peking University Beijing, China xiaofan\;Economic Law School China University of Political Science;School of Computer Science Peking University Beijing, China

Bo Ma, Hang Li, ZeHua Hu, XiaoFan Gui, LuYao Liu, Simon Lau

AI总结:

针对现有对话推荐系统在动态偏好处理、对话连贯性及多目标平衡上的不足,提出基于LLM的分层多智能体协同框架AgentRec,采用三层学习策略与自适应加权协调,在三个真实数据集上实现多项指标提升且成本可控。

摘要:

交互式对话推荐系统因能通过自然语言交互捕捉用户偏好而受到广泛关注。然而,现有方法在处理动态用户偏好、维持对话连贯性以及同时平衡多个排序目标方面面临重大挑战。本文提出了AgentRec,这是下一代基于大语言模型(LLM)的多智能体协同推荐框架,通过具备自适应智能的分层智能体网络解决上述局限。我们的方法采用专门的LLM驱动智能体分别负责对话理解、偏好建模、上下文感知和动态排序,并通过自适应加权机制进行协调,该机制可从交互模式中学习。我们提出了一种三层学习策略,结合了针对简单查询的快速响应、针对复杂偏好的智能推理以及针对高难度场景的深度协作。在三个真实世界数据集上开展的大量实验表明,AgentRec相比现有最优基线取得了持续提升:对话成功率提升2.8%,推荐准确率(NDCG@10)提升1.9%,对话效率提升3.2%,同时通过智能体协调将计算成本维持在可比水平。

英文摘要:

Interactive conversational recommender systems have gained significant attention for their ability to capture user preferences through natural language interactions. However, existing approaches face substantial challenges in handling dynamic user preferences, maintaining conversation coherence, and balancing multiple ranking objectives simultaneously. This paper introduces AgentRec, a next-generation LLM-powered multi-agent collaborative recommendation framework that addresses these limitations through hierarchical agent networks with adaptive intelligence. Our approach employs specialized LLM-powered agents for conversation understanding, preference modeling, context awareness, and dynamic ranking, coordinated through an adaptive weighting mechanism that learns from interaction patterns. We propose a three-tier learning strategy combining rapid response for simple queries, intelligent reasoning for complex preferences, and deep collaboration for challenging scenarios. Extensive experiments on three real-world datasets demonstrate that AgentRec achieves consistent improvements over state-of-the-art baselines, with 2.8\% enhancement in conversation success rate, 1.9\% improvement in recommendation accuracy (NDCG@10), and 3.2\% better conversation efficiency while maintaining comparable computational costs through intelligent agent coordination.

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。

↑