mlsanityData to 14 Oct 2026

Preference-Aware Memory Update for Long-Term LLM Agents

arXiv 2510.09720 ↗First posted 10 Oct 2025cs.CL cs.AIcited by 20

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
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.

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.

Builds on

15 of 21 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents23 Jul
  2. 2025Introspection of Thought Helps AI Agents11 Jul

Other references · 13

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2024A Survey on LLM-as-a-Judgecited by 1,423
  3. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  4. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 830
  5. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  6. 2024Understanding the planning of LLM agents: A surveycited by 421
  7. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 260
  8. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contextscited by 146
  9. 2023SCM: Enhancing Large Language Model with Self-Controlled Memory Frameworkcited by 98
  10. 2025MemInsight: Autonomous Memory Augmentation for LLM Agentscited by 85
  11. 2019OpenNRE: An Open and Extensible Toolkit for Neural Relation Extractioncited by 62
  12. 2020SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysiscited by 54
1 more
  1. 2025DatasetAgent: A Novel Multi-Agent System for Auto-Constructing Datasets from Real-World Imagescited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 19.

20 papers.

Sort:

By area:

  1. 2025MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrievalcited by 72
  2. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 44
  3. 2026TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agentscited by 31
  4. 2026Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitationscited by 21
  5. 2026From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanismscited by 21
  6. 2026MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systemscited by 16
  7. 2026AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactionscited by 12
  8. 2026NextMem: Towards Latent Factual Memory for LLM-based Agentscited by 12
  9. 2026MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversationscited by 7
  10. 2026Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agentscited by 5
  11. 2026ElasticMem: Latent Memory as a Learnable Resource for LLM Agentscited by 4
  12. 2026AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agentscited by 2
8 more
  1. 2026Agents in the Large: Perception-Centered Architecture for Persistent Agentscited by 1
  2. 2026Memory Control Signals Emerge Before Action in Long Horizon Agentscited by 1
  3. 2026From Correctness to Preference: A Framework for Personalized Agentic Reinforcement Learningcited by 0
  4. 2026ROAM: Robust Organization of Atomic Memories for Agents through Semantic Relationscited by 0
  5. 2026To Memories and Beyond: From Remembering to Knowing You across Long-Term Multimodal Personal Archivescited by 0
  6. 2026MoM: Memory of Memorycited by 0
  7. 2026AMU:Admission and Memory Update for Personalized Conversations---Structured Memory with SLM Guided Controlcited by 0
  8. 2026Learning What to Keep: Transfer-Aware Personal Skill Learning from User Feedbackcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluation
  2. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
  3. 2026RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents
  4. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
  5. 2026From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents
  6. 2026Evaluating Memory Structure in LLM Agents
  7. 2025Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
  8. 2026Choosing How to Remember: Adaptive Memory Structures for LLM Agents