Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent

2025-06-29

AI Summary

Current LLM-driven interactive recommendation agents exhibit notable limitations in understanding complex, ambiguous user intents and generalizing planning strategies. To address this, we propose TAIRA—a thought-augmented recommendation system based on a multi-agent architecture. Its core innovations are (1) a task-decomposition-driven subgoal planning mechanism and (2) “thought pattern distillation”, a novel method that extracts high-level reasoning patterns from human–agent interaction traces. These components jointly enhance planning robustness for unseen tasks and improve intent modeling fidelity. TAIRA integrates large language models, multi-agent coordination, structured task decomposition, and user behavior simulation to support diverse recommendation scenario modeling and evaluation. Extensive experiments demonstrate that TAIRA significantly outperforms state-of-the-art baselines across multiple benchmark datasets—particularly excelling in high-difficulty, low-clarity interactive recommendation tasks, where it achieves substantial gains in both accuracy and adaptability.

Technology Category

• Multiagent Systems: Multiagent Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

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.

Problem

• Enhance LLM-powered agents for complex user intents
• Improve planning in interactive recommender systems
• Address diverse and ambiguous user requests effectively

Innovation

• Thought-augmented multi-agent system for recommendations
• Thought Pattern Distillation enhances planning
• User simulation for personalized query evaluation