AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenders
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917260629639168 |
|---|---|
| author | Nguyen, Minh-Duc Kieu, Hai-Dang Le, Dung D. |
| author_facet | Nguyen, Minh-Duc Kieu, Hai-Dang Le, Dung D. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_08837 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenders Nguyen, Minh-Duc Kieu, Hai-Dang Le, Dung D. Information Retrieval Machine Learning 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. |
| title | AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenders |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2602.08837 |