AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenders
This addresses inefficiencies in LLM-based recommender systems for users by integrating collaborative filtering into agentic frameworks, though it is incremental as it builds on existing memory and CF concepts.
The paper tackles the problem of agentic LLM-based recommender systems lacking collaborative filtering signals by proposing AMEM4Rec, which learns these signals through cross-user memory evolution, resulting in consistent outperformance over state-of-the-art LLM-based recommenders on Amazon and MIND datasets.
Agentic systems powered by Large Language Models (LLMs) have shown strong potential in recommender systems but remain hindered by several challenges. Fine-tuning LLMs is parameter-inefficient, and prompt-based agentic reasoning is limited by context length and hallucination risk. Moreover, existing agentic recommendation systems predominantly leverages semantic knowledge while neglecting the collaborative filtering (CF) signals essential for implicit preference modeling. To address these limitations, we propose AMEM4Rec, an agentic LLM-based recommender that learns collaborative signals in an end-to-end manner through cross-user memory evolution. AMEM4Rec stores abstract user behavior patterns from user histories in a global memory pool. Within this pool, memories are linked to similar existing ones and iteratively evolved to reinforce shared cross-user patterns, enabling the system to become aware of CF signals without relying on a pre-trained CF model. Extensive experiments on Amazon and MIND datasets show that AMEM4Rec consistently outperforms state-of-the-art LLM-based recommenders, demonstrating the effectiveness of evolving memory-guided collaborative filtering.