Agentic Feedback Loop Modeling Improves Recommendation and User Simulation

TL;DR

This paper introduces a novel feedback loop framework between recommendation and user agents, significantly improving recommendation accuracy and user simulation without increasing bias, validated through extensive experiments.

Contribution

The paper presents a new agentic feedback loop framework that enhances collaboration between recommendation and user agents, improving inference and recommendation quality.

Findings

11.52% improvement over single recommendation agent

21.12% improvement over single user agent

Robustness against popularity and position bias

Abstract

Large language model-based agents are increasingly applied in the recommendation field due to their extensive knowledge and strong planning capabilities. While prior research has primarily focused on enhancing either the recommendation agent or the user agent individually, the collaborative interaction between the two has often been overlooked. Towards this research gap, we propose a novel framework that emphasizes the feedback loop process to facilitate the collaboration between the recommendation agent and the user agent. Specifically, the recommendation agent refines its understanding of user preferences by analyzing the feedback from the user agent on the item recommendation. Conversely, the user agent further identifies potential user interests based on the items and recommendation reasons provided by the recommendation agent. This iterative process enhances the ability of both agents to infer user behaviors, enabling more effective item recommendations and more accurate user simulations. Extensive experiments on three datasets demonstrate the effectiveness of the agentic feedback loop: the agentic feedback loop yields an average improvement of 11.52% over the single recommendation agent and 21.12% over the single user agent. Furthermore, the results show that the agentic feedback loop does not exacerbate popularity or position bias, which are typically amplified by the real-world feedback loop, highlighting its robustness. The source code is available at https://github.com/Lanyu0303/AFL.