Search papers, labs, and topics across Lattice.
This paper introduces the PRTA framework, which utilizes an LLM as a central planner that interacts with multiple recommendation models to enhance personalized recommendation tasks. By integrating reflection mechanisms for tool selection based on user profiles, the framework effectively mitigates issues of hallucination and context-length limitations inherent in traditional LLMs. Experimental results across three public datasets reveal that PRTA significantly outperforms both conventional recommendation systems and existing LLM-based approaches in full-ranking recommendation performance.
PRTA outperforms traditional and LLM-based recommendation systems by effectively leveraging multiple models through a central LLM planner, enhancing personalization without the pitfalls of hallucination.
Although large language models (LLMs) have recently gained traction in recommender systems due to their strong reasoning capabilities and extensive world knowledge, previous LLM-based agents suffer from hallucination and context-length limitations, and thus are not suitable for full-ranking recommendation tasks. To circumvent these limitations through architectural design rather than modifying the LLM itself, we propose an agent-based recommendation framework, memory-based $\textbf{P}$ersonalized $\textbf{R}$ecommendation $\textbf{T}$ool learning via autonomous language $\textbf{A}$gents (PRTA), in which an LLM acts as a central planner interacting with multiple recommendation models as tools. The LLM-based agent is responsible for high-level reasoning and personalized tool selection, while traditional recommendation models perform full-ranking scoring, leveraging their scalability in modeling behavioral patterns. To support personalized tool selection, we design reflection mechanisms that enable the agent to evaluate and compare tools for each user based on user profiles and candidate ranked lists. Extensive experiments across three public datasets demonstrate the superiority of \modelname over traditional recommendation and LLM-based baselines in improving full-ranking recommendation performance.
Microsoft Research