用思维模式提炼增强大模型推荐智能，更好理解复杂用户需求。
Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent
- 通过思维模式提炼技术，让推荐代理分步规划复杂需求。
- 在多个数据集上表现优于现有方法，尤其在困难任务中提升显著。
- 适合需要精准理解模糊或动态需求的交互式推荐场景。
交互式推荐是一种典型的信息获取任务，允许用户通过自然语言交互表达需求并获得个性化推荐。基于大语言模型（LLM）的代理已成为交互式推荐的新范式，能有效捕捉用户实时需求，提升个性化体验。然而，由于规划和泛化能力有限，现有方法难以应对多样且复杂的用户意图，如直觉性、不明确或偶尔模糊的请求。为此，我们提出一种新型思维增强型交互式推荐代理系统（TAIRA），通过提炼的思维模式应对复杂用户意图。TAIRA设计为一个由管理代理协调的多代理系统，该代理通过分解用户需求并规划子任务来执行推荐，其规划能力通过思维模式提炼（TPD）得到强化——TPD从代理与人类专家的经验中提取高层级思维。此外，我们设计了多种用户模拟方案，生成不同难度的个性化查询，并基于特定数据集评估推荐效果。在多个数据集上的综合实验表明，相比现有方法，TAIRA性能显著提升，尤其在更具挑战性的任务中优势更明显，且在新任务上具有良好的泛化能力，进一步验证了其在处理复杂用户意图方面的优越性。代码已公开于：https://github.com/Alcein/TAIRA。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。