mlsanityData to 14 Oct 2026

FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory

arXiv 2604.20300 ↗First posted 22 Apr 2026cs.AIcited by 3

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

Abstract (arXiv)

For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting--inspired by human cognitive processes (hippocampal indexing/consolidation theory and Ebbinghaus forgetting curve)--remains underexplored. We argue that in resource-constrained environments, a well-designed forgetting mechanism is as crucial as remembering, delivering benefits across three dimensions: (1) efficiency via intelligent memory pruning, (2) quality by dynamically updating outdated preferences and context, and (3) security through active forgetting of malicious inputs, sensitive data, and privacy-compromising content. Our framework establishes a taxonomy of forgetting mechanisms: passive decay-based, active deletion-based, safety-triggered, and adaptive reinforcement-based. Building on advances in LLM agent architectures and vector databases, we present detailed specifications, implementation strategies, and empirical validation from controlled experiments. Results show significant improvements: access efficiency (+8.49%), content quality (+29.2% signal-to-noise ratio), and security performance (100% elimination of security risks). Our work bridges cognitive neuroscience and AI systems, offering practical solutions for real-world deployment while addressing ethical and regulatory compliance. The paper concludes with challenges and future directions, establishing selective forgetting as a fundamental capability for next-generation LLM agents operating in real-world, resource-constrained scenarios. Our contributions align with AI-native memory systems and responsible AI development.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 46 of its 83 references that are in the map. First posted on arXiv 22 Apr 2026.

Builds on

46 of 83 references.

Closest ancestors · 4

Same direction, newest first

  1. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers8 Mar
  2. 2026FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory26 Jan
  3. 2026LSTM-MAS: A Long Short-Term Memory Inspired Multi-Agent System for Long-Context Understanding17 Jan
  4. 2025From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory11 Nov

Other references · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  7. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  8. 2020Scaling Laws for Neural Language Modelscited by 6,586
  9. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  10. 2017Billion-scale similarity search with GPUscited by 2,497
  11. 2020Extracting Training Data from Large Language Modelscited by 2,189
  12. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
30 more
  1. 2016Concrete Problems in AI Safetycited by 1,642
  2. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,420
  3. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  4. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  5. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  6. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
  7. 2020Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditingcited by 384
  8. 2018Deep Learning: A Critical Appraisalcited by 217
  9. 2018The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigationcited by 165
  10. 2019The Ethics of AI Ethics -- An Evaluation of Guidelinescited by 129
  11. 2025MemVerse: Multimodal Memory for Lifelong Learning Agentscited by 35
  12. 2025Continual Learning via Sparse Memory Finetuningcited by 20
  13. 2025Merge before Forget: A Single LoRA Continual Learning via Continual Mergingcited by 11
  14. 2025Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learningcited by 10
  15. 2026FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learningcited by 8
  16. 2026Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learningcited by 8
  17. 2026Learning to Forget: Sleep-Inspired Memory Consolidation for Resolving Proactive Interference in Large Language Modelscited by 7
  18. 2025Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearningcited by 6
  19. 2026CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Managementcited by 5
  20. 2026Memory Bank Compression for Continual Adaptation of Large Language Modelscited by 4
  21. 2026MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuningcited by 4
  22. 2025Unlearning Imperative: Securing Trustworthy and Responsible LLMs through Engineered Forgettingcited by 2
  23. 2026AllMem: A Memory-centric Recipe for Efficient Long-context Modelingcited by 2
  24. 2026Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columnscited by 2
  25. 2026StatePlane: A Cognitive State Plane for Long-Horizon AI Systems Under Bounded Contextcited by 2
  26. 2026Trained Persistent Memory for Frozen Encoder--Decoder LLMs: Six Architectural Methodscited by 2
  27. 2026MemCoT: Test-Time Scaling through Memory-Driven Chain-of-Thoughtcited by 2
  28. 2025COLA: Continual Learning via Autoencoder Retrieval of Adapterscited by 1
  29. 2026Improving Sparse Memory Finetuningcited by 1
  30. 2026From Anchors to Supervision: Memory-Graph Guided Corpus-Free Unlearning for Large Language Modelscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Codingcited by 3
  2. 2026Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agentscited by 2
  3. 2026Remember Before You're Asked: MemDream for Self-Probing Memory Evolutioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Forgetful but Faithful: A Cognitive Memory Architecture and Benchmark for Privacy-Aware Generative Agents
  2. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents
  3. 2026Oblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activation
  4. 2026When to Forget: A Memory Governance Primitive
  5. 2026Selective Memory Retention for Long-Horizon LLM Agents
  6. 2026SF-AMS: Strategic Forgetting for Structured Memory in LLM Agent
  7. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
  8. 2026Contextual Agentic Memory is a Memo, Not True Memory