RecNet: Self-Evolving Preference Propagation for Agentic Recommender Systems

2026-01-29

AI Summary

This work addresses the limitations of existing large language model (LLM)-based recommender systems, which rely on sparse and noisy explicit interactions and struggle to capture the real-time, dynamic interplay between users and items. To overcome this, we propose RecNet, a novel framework that integrates user-item preferences through a two-stage mechanism: forward preference routing propagation followed by backward feedback-driven optimization. RecNet introduces a learnable rule-based memory filter and a multi-agent reinforcement learning feedback loop, synergistically combining LLM-powered router agents, message buffers, and a credit assignment mechanism to enable dynamic, personalized preference updates and continuous system self-evolution. Extensive experiments demonstrate that RecNet significantly outperforms existing approaches across diverse scenarios, validating its effectiveness in real-time preference modeling and autonomous system adaptation.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Multiagent Systems: Multiagent Learning
• 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: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Agentic Recommender Systems
• Preference Propagation
• Large Language Models
• User-Item Interactions
• Real-time Influence

Innovation

• preference propagation
• agentic recommender systems
• self-evolving framework
• multi-agent reinforcement learning
• large language models