mlsanityData to 7 Oct 2026

What Deserves Memory: Adaptive Memory Distillation for LLM Agents

arXiv 2508.03341 ↗First posted 5 Aug 2025cs.AIcited by 46

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

Memory systems for LLM agents struggle to determine what information deserves retention. Existing approaches rely on predefined heuristics such as importance scores, emotional tags, or factual templates, encoding designer intuition rather than learning from the data itself. Inspired by cognitive ideas, we propose NEMORI, an adaptive memory distillation framework that casts the assessment of experience's future utility as a matter of predictability. Specifically, NEMORI comprises two cascading modules: Episodic Memory Integration transforms raw interactions into coherent narratives, and Semantic Knowledge Distillation extracts insights via prediction error. Centering on distillation, the framework remains agnostic to downstream management. Extensive experiments confirm that NEMORI achieves strong performance, efficiency, and storage reduction. Our work suggests that observing the intrinsic properties of interaction sequences offers a viable, data-driven alternative to heuristic-based memory design. Code: https://github.com/nemori-ai/nemori.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 10 of its 25 references that are in the map. First posted on arXiv 5 Aug 2025.

Builds on

10 of 25 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  2. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memory20 Jan
  3. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents5 Jul
  4. 2024Hello Again! LLM-powered Personalized Agent for Long-term Dialogue9 Jun
  5. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 5

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  3. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  4. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
  5. 2024Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrievalcited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 38.

46 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 285
  2. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 163
  3. 2026EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoningcited by 52
  4. 2025Mem-α: Learning Memory Construction via Reinforcement Learningcited by 49
  5. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  6. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
  7. 2026TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agentscited by 26
  8. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 22
  9. 2026AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversationscited by 20
  10. 2025A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agentscited by 18
  11. 2026HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agentscited by 16
  12. 2026Learning to Continually Learn via Meta-learning Agentic Memory Designscited by 16
34 more
  1. 2026Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Frameworkcited by 16
  2. 2026APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AIcited by 16
  3. 2025TeleMem: Building Long-Term and Multimodal Memory for Agentic AIcited by 14
  4. 2026HyperMem: Hypergraph Memory for Long-Term Conversationscited by 14
  5. 2025MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environmentscited by 13
  6. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  7. 2026Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directionscited by 10
  8. 2026Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memorycited by 9
  9. 2025Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AIcited by 8
  10. 2026SmartSearch: How Ranking Beats Structure for Conversational Memory Retrievalcited by 5
  11. 2026D-Mem: A Dual-Process Memory System for LLM Agentscited by 5
  12. 2026Mitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory Representationcited by 5
  13. 2026EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agentscited by 5
  14. 2026RaMem: Contextual Reinstatement for Long-term Agentic Memorycited by 5
  15. 2026ES-Mem: Event Segmentation-Based Memory for Long-Term Dialogue Agentscited by 4
  16. 2026MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGscited by 4
  17. 2026MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoningcited by 3
  18. 2026TraceMem: Weaving Narrative Memory Schemata from User Conversational Tracescited by 2
  19. 2026ByteRover: Agent-Native Memory Through LLM-Curated Hierarchical Contextcited by 2
  20. 2026MemCoT: Test-Time Scaling through Memory-Driven Chain-of-Thoughtcited by 2
  21. 2026AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agentscited by 2
  22. 2026Enhancing Conversational Agents via Task-Oriented Adversarial Memory Adaptationcited by 1
  23. 2026Opal: Private Memory for Personal AIcited by 1
  24. 2026TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillationcited by 1
  25. 2026Rethinking Memory as Continuously Evolving Connectivitycited by 1
  26. 2026MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-offcited by 1
  27. 2026Towards Autonomous Memory Agentscited by 0
  28. 2026Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluationcited by 0
  29. 2026PSD: Pseudo Self-Distillation of Memory Representation Capabilities for LLM Agentscited by 0
  30. 2026EnSIMem: Entity-Structured Indexing for Long-Term Agent Memorycited by 0
  31. 2026Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agentscited by 0
  32. 2026C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Taskscited by 0
  33. 2026Remember by Asking: Retrieval-Induced Memory Evolution for LLM Agentscited by 0
  34. 2026Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
  2. 2025Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
  3. 2026Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
  4. 2026Memory Beyond Recall: A Dual-Process Cognitive Memory System for Self-Evolving LLM Agents
  5. 2026AdMem: Advanced Memory for Task-solving Agents
  6. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
  7. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
  8. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers