# From Atom to Community: Structured and Evolving Agent Memory for User Behavior Modeling

arXiv: https://arxiv.org/abs/2601.16872 · HTML: https://mlsanity.com/paper/2601.16872/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 54 references that are in the map.
- First posted on arXiv 23 Jan 2026.

## Placed in

- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)

## Builds on (most cited first, 30 of 30)

- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [Large Language Models are Zero-Shot Rankers for Recommender Systems](https://mlsanity.com/paper/2305.08845/) (2023)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives](https://mlsanity.com/paper/2312.11970/) (2023)
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey](https://mlsanity.com/paper/2404.11584/) (2024)
- [Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations](https://mlsanity.com/paper/2308.16505/) (2023)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems](https://mlsanity.com/paper/2310.09233/) (2023)
- [In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents](https://mlsanity.com/paper/2503.08026/) (2025)
- [Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory](https://mlsanity.com/paper/2508.09736/) (2025)
- [Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving](https://mlsanity.com/paper/2507.06229/) (2025)
- [From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs](https://mlsanity.com/paper/2410.14052/) (2024)
- [Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents](https://mlsanity.com/paper/2507.22925/) (2025)
- [MACRec: a Multi-Agent Collaboration Framework for Recommendation](https://mlsanity.com/paper/2402.15235/) (2024)
- [Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning](https://mlsanity.com/paper/2405.15114/) (2024)
- [A Survey on LLM-powered Agents for Recommender Systems](https://mlsanity.com/paper/2502.10050/) (2025)
- [A Multi-Agent Conversational Recommender System](https://mlsanity.com/paper/2402.01135/) (2024)
- [A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval](https://mlsanity.com/paper/2503.05659/) (2025)
- [RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agents](https://mlsanity.com/paper/2308.09904/) (2023)
- [AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations](https://mlsanity.com/paper/2502.13843/) (2025)
- [MemoCRS: Memory-enhanced Sequential Conversational Recommender Systems with Large Language Models](https://mlsanity.com/paper/2407.04960/) (2024)
- [MemRec: Collaborative Memory-Augmented Agentic Recommender System](https://mlsanity.com/paper/2601.08816/) (2026)
- [Knowledge Graph Enhanced Language Agents for Recommendation](https://mlsanity.com/paper/2410.19627/) (2024)
- [Theoretical Modeling of the Iterative Properties of User Discovery in a Collaborative Filtering Recommender System](https://mlsanity.com/paper/2008.13526/) (2020)

## Built on by (most cited first, 3 of 3)

- [Agentic Recommender System with Hierarchical Belief-State Memory](https://mlsanity.com/paper/2605.14401/) (2026)
- [LeanMem: Simple and Efficient Long-Term Memory for LLM Agents](https://mlsanity.com/paper/2608.03463/) (2026)
- [CORAL: An LLM-Native Harness for Production Recommender Systems](https://mlsanity.com/paper/2609.02730/) (2026)

## Abstract (arXiv)

User behavior modeling lies at the heart of personalized applications like recommender systems. With LLM-based agents, user preference representation has evolved from latent embeddings to semantic memory. While existing memory mechanisms show promise in textual dialogues, modeling non-textual behaviors remains challenging, as preferences must be inferred from implicit signals like clicks without ground truth supervision. Current approaches rely on a single unstructured summary, updated through simple overwriting. However, this is suboptimal: users exhibit multi-faceted interests that get conflated, preferences evolve yet naive overwriting causes forgetting, and sparse individual interactions necessitate collaborative signals. We present STEAM (textitSTructured and Evolving Agent Memory), a novel framework that reimagines how agent memory is organized and updated. STEAM decomposes preferences into atomic memory units, each capturing a distinct interest dimension with explicit links to observed behaviors. To exploit collaborative patterns, STEAM organizes similar memories across users into communities and generates prototype memories for signal propagation. The framework further incorporates adaptive evolution mechanisms, including consolidation for refining memories and formation for capturing emerging interests. Experiments on three real-world datasets demonstrate that STEAM substantially outperforms state-of-the-art baselines in recommendation accuracy, simulation fidelity, and diversity.