Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent

TL;DR

This paper introduces TAIRA, a thought-augmented multi-agent system that improves interactive recommendation by decomposing user needs and utilizing thought patterns, leading to better handling of complex and ambiguous user requests.

Contribution

The paper presents TAIRA, a novel LLM-powered multi-agent framework with Thought Pattern Distillation to enhance planning and generalization in interactive recommendation tasks.

Findings

TAIRA outperforms existing methods on multiple datasets.

TAIRA shows significant improvements on challenging tasks.

TAIRA generalizes well to novel user queries.

Abstract

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.