# Preference-Aware Memory Update for Long-Term LLM Agents arXiv: https://arxiv.org/abs/2510.09720 ยท HTML: https://mlsanity.com/paper/2510.09720/ ## Key facts - Cited by 20 papers in the map (data through 14 Oct 2026). - Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. - Builds on 15 of its 21 references that are in the map. - First posted on arXiv 10 Oct 2025. ## Placed in - LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/) - LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/) ## Builds on (most cited first, 15 of 15) - [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023) - [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024) - [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025) - [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024) - [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024) - [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024) - [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024) - [A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts](https://mlsanity.com/paper/2402.09727/) (2024) - [SCM: Enhancing Large Language Model with Self-Controlled Memory Framework](https://mlsanity.com/paper/2304.13343/) (2023) - [MemInsight: Autonomous Memory Augmentation for LLM Agents](https://mlsanity.com/paper/2503.21760/) (2025) - [OpenNRE: An Open and Extensible Toolkit for Neural Relation Extraction](https://mlsanity.com/paper/1909.13078/) (2019) - [Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents](https://mlsanity.com/paper/2507.22925/) (2025) - [SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis](https://mlsanity.com/paper/2005.05635/) (2020) - [DatasetAgent: A Novel Multi-Agent System for Auto-Constructing Datasets from Real-World Images](https://mlsanity.com/paper/2507.08648/) (2025) - [Introspection of Thought Helps AI Agents](https://mlsanity.com/paper/2507.08664/) (2025) ## Built on by (most cited first, 20 of 20) - [MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval](https://mlsanity.com/paper/2512.16962/) (2025) - [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (2026) - [TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents](https://mlsanity.com/paper/2601.02845/) (2026) - [Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations](https://mlsanity.com/paper/2602.19320/) (2026) - [From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms](https://mlsanity.com/paper/2605.06716/) (2026) - [MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systems](https://mlsanity.com/paper/2605.25002/) (2026) - [AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions](https://mlsanity.com/paper/2602.06008/) (2026) - [NextMem: Towards Latent Factual Memory for LLM-based Agents](https://mlsanity.com/paper/2603.15634/) (2026) - [MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations](https://mlsanity.com/paper/2607.12893/) (2026) - [Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents](https://mlsanity.com/paper/2606.13174/) (2026) - [ElasticMem: Latent Memory as a Learnable Resource for LLM Agents](https://mlsanity.com/paper/2605.30690/) (2026) - [AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agents](https://mlsanity.com/paper/2606.21144/) (2026) - [Agents in the Large: Perception-Centered Architecture for Persistent Agents](https://mlsanity.com/paper/2608.30478/) (2026) - [Memory Control Signals Emerge Before Action in Long Horizon Agents](https://mlsanity.com/paper/2609.27286/) (2026) - [From Correctness to Preference: A Framework for Personalized Agentic Reinforcement Learning](https://mlsanity.com/paper/2605.23382/) (2026) - [ROAM: Robust Organization of Atomic Memories for Agents through Semantic Relations](https://mlsanity.com/paper/2609.09778/) (2026) - [To Memories and Beyond: From Remembering to Knowing You across Long-Term Multimodal Personal Archives](https://mlsanity.com/paper/2609.19167/) (2026) - [MoM: Memory of Memory](https://mlsanity.com/paper/2609.25054/) (2026) - [AMU:Admission and Memory Update for Personalized Conversations---Structured Memory with SLM Guided Control](https://mlsanity.com/paper/2609.36976/) (2026) - [Learning What to Keep: Transfer-Aware Personal Skill Learning from User Feedback](https://mlsanity.com/paper/2610.19380/) (2026) ## Abstract (arXiv) One of the key factors influencing the reasoning capabilities of LLM-based agents is their ability to leverage long-term memory. Integrating long-term memory mechanisms allows agents to make informed decisions grounded in historical interactions. While recent advances have significantly improved the storage and retrieval components, by encoding memory into dense vectors for similarity search or organizing memory as structured knowledge graphs most existing approaches fall short in memory updating. In particular, they lack mechanisms for dynamically refining preference memory representations in response to evolving user behaviors and contexts. To address this gap, we propose a Preference-Aware Memory Update Mechanism (PAMU) that enables dynamic and personalized memory refinement. By integrating sliding window averages (SW) with exponential moving averages (EMA), PAMU constructs a fused preference-aware representation that captures both short-term fluctuations and long-term user tendencies. We conduct experiments on five task scenarios of the LoCoMo dataset, and the results show that our mechanism can significantly improve the output quality of LLM in five baselines, validating its effectiveness in long-term conversations.