面向LLM驱动的交互式推荐智能体的思维增强规划
Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent
AI总结：
针对LLM驱动的交互式推荐智能体难以处理复杂用户意图的问题，提出基于思维模式蒸馏的多智能体系统TAIRA，通过提取专家经验增强管理智能体的规划能力，在多数据集实验中显著提升了推荐性能并展现出强大的泛化优势。
摘要：
交互式推荐是一种典型的信息检索任务，允许用户通过自然语言交互式地表达需求并获取个性化推荐。由大型语言模型驱动的（LLM-powered）智能体已成为交互式推荐中的新范式，能够有效捕获用户的实时需求并增强个性化体验。然而，由于规划和泛化能力有限，现有LLM驱动的交互式推荐智能体难以有效处理多样且复杂的用户意图，例如直觉的、未精炼的或偶尔模糊的请求。为了应对这一挑战，我们提出了一种新颖的思维增强交互式推荐智能体系统（TAIRA），通过提炼的思维模式来处理复杂的用户意图。具体而言，TAIRA被设计为一个LLM驱动的多智能体系统，其特色是一个管理智能体，通过分解用户需求和规划子任务来编排推荐任务，其规划能力通过思维模式蒸馏（TPD）得到加强。TPD是一种思维增强方法，从智能体和人类专家的经验中提取高层思维。此外，我们设计了一组用户模拟方案，以生成不同难度的个性化查询，并基于特定数据集评估推荐结果。通过在多个数据集上进行的综合实验，与现有方法相比，TAIRA表现出显著提升的性能。值得注意的是，TAIRA在更具挑战性的任务上展现出更大的优势，同时在新型任务上有效泛化，进一步验证了其在交互式推荐系统中管理复杂用户意图的优越性。代码公开于：https://github.com/Alcein/TAIRA。
英文摘要：
Interactive recommendation is a typical information-seeking task that allows users to interactively express their needs through natural language and obtain personalized recommendations. Large language model-powered (LLM-powered) agents have become a new paradigm in interactive recommendations, effectively capturing users' real-time needs and enhancing personalized experiences. However, due to limited planning and generalization capabilities, existing formulations of LLM-powered interactive recommender agents struggle to effectively address diverse and complex user intents, such as intuitive, unrefined, or occasionally ambiguous requests. To tackle this challenge, we propose a novel thought-augmented interactive recommender agent system (TAIRA) that addresses complex user intents through distilled thought patterns. Specifically, TAIRA is designed as an LLM-powered multi-agent system featuring a manager agent that orchestrates recommendation tasks by decomposing user needs and planning subtasks, with its planning capacity strengthened through Thought Pattern Distillation (TPD), a thought-augmentation method that extracts high-level thoughts from the agent's and human experts' experiences. Moreover, we designed a set of user simulation schemes to generate personalized queries of different difficulties and evaluate the recommendations based on specific datasets. Through comprehensive experiments conducted across multiple datasets, TAIRA exhibits significantly enhanced performance compared to existing methods. Notably, TAIRA shows a greater advantage on more challenging tasks while generalizing effectively on novel tasks, further validating its superiority in managing complex user intents within interactive recommendation systems. The code is publicly available at:https://github.com/Alcein/TAIRA.
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。
