AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenders

• URL: http://arxiv.org/abs/2602.08837v1
• Date: Mon, 09 Feb 2026 16:06:55 GMT
• Title: AMEM4Rec: Leveraging Cross-User Similarity for Memory Evolution in Agentic LLM Recommenders
• Authors: Minh-Duc Nguyen, Hai-Dang Kieu, Dung D. Le,
• Abstract summary: AMEM4Rec is an agentic recommender that learns collaborative signals in an end-to-end manner through cross-user memory evolution.<n>Experiments on Amazon and MIND datasets show that AMEM4Rec consistently outperforms state-of-the-art LLM-based recommenders.
• Score: 5.664940585902205
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMs [23.593398623128735]
  MR.Rec is a novel framework that synergizes memory and reasoning for Large Language Models (LLMs)-based recommendations.<n>To achieve personalization, we develop a comprehensive Retrieval-Augmented Generation (RAG) system that efficiently indexes and retrieves relevant external memory.<n>By combining dynamic memory retrieval with adaptive reasoning, this approach ensures more accurate, context-aware, and highly personalized recommendations.
  arXiv  Detail & Related papers  (2025-10-16T12:40:48Z)
• AgentDR Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents [42.177723613925146]
  We propose a novel LLM-agent framework, AgenDR, which bridges LLM reasoning with scalable recommendation tools.<n>Our approach delegates full-ranking tasks to traditional models while utilizing LLMs to integrate multiple recommendation outputs.<n>We show that our framework achieves superior full-ranking performance, yielding on average a twofold improvement over its underlying tools.
  arXiv  Detail & Related papers  (2025-10-07T05:48:05Z)
• Beyond Semantic Understanding: Preserving Collaborative Frequency Components in LLM-based Recommendation [7.014265360936046]
  FreLLM4Rec is an approach designed to balance semantic and collaborative information from a spectral perspective.<n>Experiments on four benchmark datasets demonstrate that FreLLM4Rec successfully mitigates collaborative signal attenuation.
  arXiv  Detail & Related papers  (2025-08-14T03:33:02Z)
• LLM4MEA: Data-free Model Extraction Attacks on Sequential Recommenders via Large Language Models [50.794651919028965]
  Recent studies have demonstrated the vulnerability of sequential recommender systems to Model Extraction Attacks (MEAs)<n>Black-box attacks in prior MEAs are ineffective at exposing recommender system vulnerabilities due to random sampling in data selection.<n>We propose LLM4MEA, a novel model extraction method that leverages Large Language Models (LLMs) as human-like rankers to generate data.
  arXiv  Detail & Related papers  (2025-07-22T19:20:23Z)
• LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation [49.78419076215196]
  Sequential recommendation aims to predict users' future interactions by modeling collaborative filtering (CF) signals from historical behaviors of similar users or items.<n>Traditional sequential recommenders rely on ID-based embeddings, which capture CF signals through high-order co-occurrence patterns.<n>Recent advances in large language models (LLMs) have motivated text-based recommendation approaches that derive item representations from textual descriptions.<n>We argue that an ideal embedding model should seamlessly integrate CF signals with rich semantic representations to improve both in-domain and out-of-domain recommendation performance.
  arXiv  Detail & Related papers  (2025-06-16T13:27:06Z)
• What LLMs Miss in Recommendations: Bridging the Gap with Retrieval-Augmented Collaborative Signals [4.297070083645049]
  User-item interactions contain rich collaborative signals that form the backbone of many successful recommender systems.<n>It remains unclear whether large language models (LLMs) can effectively reason over this type of collaborative information.<n>We introduce a simple retrieval-augmented generation (RAG) method that enhances LLMs by grounding their predictions in structured interaction data.
  arXiv  Detail & Related papers  (2025-05-27T05:18:57Z)
• Bidirectional Knowledge Distillation for Enhancing Sequential Recommendation with Large Language Models [28.559223475725137]
  Large language models (LLMs) have demonstrated exceptional performance in understanding and generating semantic patterns.<n>LLMs often face challenges related to high inference costs and static knowledge transfer methods.<n>We propose a novel mutual distillation framework, LLMD4Rec, that fosters dynamic and bidirectional knowledge exchange.
  arXiv  Detail & Related papers  (2025-05-23T17:21:14Z)
• EAGER-LLM: Enhancing Large Language Models as Recommenders through Exogenous Behavior-Semantic Integration [60.47645731801866]
  Large language models (LLMs) are increasingly leveraged as foundational backbones in advanced recommender systems.<n>LLMs are pre-trained linguistic semantics but learn collaborative semantics from scratch via the llm-Backbone.<n>We propose EAGER-LLM, a decoder-only generative recommendation framework that integrates endogenous and endogenous behavioral and semantic information in a non-intrusive manner.
  arXiv  Detail & Related papers  (2025-02-20T17:01:57Z)
• LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation [57.49045064294086]
  Large Language Model (LLM) has the ability to capture semantic relationships between items, independent of their popularity.<n>We introduce LLMEmb, a novel method leveraging LLM to generate item embeddings that enhance Sequential Recommender Systems (SRS) performance.
  arXiv  Detail & Related papers  (2024-09-30T03:59:06Z)
• Beyond Inter-Item Relations: Dynamic Adaption for Enhancing LLM-Based Sequential Recommendation [83.87767101732351]
  Sequential recommender systems (SRS) predict the next items that users may prefer based on user historical interaction sequences. Inspired by the rise of large language models (LLMs) in various AI applications, there is a surge of work on LLM-based SRS. We propose DARec, a sequential recommendation model built on top of coarse-grained adaption for capturing inter-item relations.
  arXiv  Detail & Related papers  (2024-08-14T10:03:40Z)
• LLM4MSR: An LLM-Enhanced Paradigm for Multi-Scenario Recommendation [52.55639178180821]
  The study on multi-scenario recommendation (MSR) has attracted much attention, which uses the data from all scenarios to simultaneously improve their recommendation performance.<n>Existing methods tend to integrate insufficient scenario knowledge and neglect learning personalized cross-scenario preferences, thus leading to sub-optimal performance.<n>We propose a large language model (LLM)-enhanced paradigm LLM4MSR to fill these gaps.
  arXiv  Detail & Related papers  (2024-06-18T11:59:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.