RecNet: Self-Evolving Preference Propagation for Agentic Recommender Systems

TL;DR

RecNet introduces a self-evolving framework for recommender systems that dynamically propagates real-time user preferences across related entities, improving personalization by modeling mutual influences more effectively.

Contribution

It proposes a novel preference propagation framework with a dual-phase mechanism, integrating reinforcement learning and personalized preference reception for continuous self-evolution.

Findings

RecNet outperforms existing methods in modeling preference dynamics.

The framework effectively captures real-time mutual influences among users and items.

Experimental results show improved recommendation accuracy across scenarios.

Abstract

Agentic recommender systems leverage Large Language Models (LLMs) to model complex user behaviors and support personalized decision-making. However, existing methods primarily model preference changes based on explicit user-item interactions, which are sparse, noisy, and unable to reflect the real-time, mutual influences among users and items. To address these limitations, we propose RecNet, a self-evolving preference propagation framework that proactively propagates real-time preference updates across related users and items. RecNet consists of two complementary phases. In the forward phase, the centralized preference routing mechanism leverages router agents to integrate preference updates and dynamically propagate them to the most relevant agents. To ensure accurate and personalized integration of propagated preferences, we further introduce a personalized preference reception mechanism, which combines a message buffer for temporary caching and an optimizable, rule-based filter memory to guide selective preference assimilation based on past experience and interests. In the backward phase, the feedback-driven propagation optimization mechanism simulates a multi-agent reinforcement learning framework, using LLMs for credit assignment, gradient analysis, and module-level optimization, enabling continuous self-evolution of propagation strategies. Extensive experiments on various scenarios demonstrate the effectiveness of RecNet in modeling preference propagation for recommender systems.