记忆压缩与遗忘

选择性遗忘、记忆压缩、重要性判定

共 31 篇论文，自动生成于 2026-05-13

论文列表

• "AOI: Context-Aware Multi-Agent Operations via Dynamic Scheduling and Hierarchical Memory Compression" — arXiv:2512.13956
• ApCM Model: Auxiliary-Predicted Compress Memory for Neural Memory Storage — arXiv:2601.11609
• "Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning" — arXiv:2511.20196
• "Clustering-Driven Memory Compression for On-device Large Language Models" — arXiv:2601.17443
• "CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models" — arXiv:2412.07393
• "ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents" — arXiv:2604.23069
• "Cross-Modal Memory Compression for Efficient Multi-Agent Debate" — arXiv:2602.00454
• "Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory" — arXiv:2605.10870
• "Learning to Forget: Continual Learning with Adaptive Weight Decay" — arXiv:2604.27063
• "Goal-Directed Search Outperforms Goal-Agnostic Memory Compression in Long-Context Memory Tasks" — arXiv:2511.21726
• "Learning to Forget: Hierarchical Episodic Memory for Lifelong Robot Deployment" — arXiv:2604.11306
• "Hidden Failure Modes of Gradient Modification under Adam in Continual Learning, and Adaptive Decoupled Moment Routing as a Repair" — arXiv:2604.22407
• Human-Inspired Memory Architecture for LLM Agents — arXiv:2605.08538
• "LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents" — arXiv:"2605.05191"
• "Mela: Test-Time Memory Consolidation based on Transformation Hypothesis" — arXiv:2605.10537
• "MELODI: Exploring Memory Compression for Long Contexts" — arXiv:2410.03156
• "MemArchitect: A Policy Driven Memory Governance Layer" — arXiv:2603.18330
• "MemCoE: Learning How and What to Memorize — Cognition-Inspired Two-Stage Optimization for Evolving Memory" — arXiv:2605.00702
• "Memini: Continual Knowledge Updating in LLM Systems Through Multi-Timescale Memory Dynamics" — arXiv:"2605.05097"
• "Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models" — arXiv:2605.07721
• "Novel Memory Forgetting Techniques for Autonomous AI Agents: Balancing Relevance and Efficiency" — arXiv:2604.02280
• "The Price of Meaning: Why Every Semantic Memory System Forgets" — arXiv:"2603.27116"
• "RMAAT: Astrocyte-Inspired Memory Compression and Replay for Efficient Long-Context Transformers" — arXiv:2601.00426
• "ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting" — arXiv:2605.03804
• "Selective Forgetting for Large Reasoning Models" — arXiv:2604.03571
• "SleepGate: Sleep-Inspired Memory Consolidation for Resolving Proactive Interference in LLMs" — arXiv:2603.14517
• "StreamMeCo: Streaming Memory Compression for Video Understanding Agents" — arXiv:2604.09000
• "Structured Distillation for Personalized Agent Memory: 11x Token Reduction with Retrieval Preservation" — arXiv:2603.13017
• "SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems" — arXiv:2604.04514
• "When to Forget: A Memory Governance Primitive" — arXiv:2604.12007
• "Human-like Working Memory Interference in Large Language Models" — arXiv:"2604.09670"