让AI agent像人一样主动遗忘，提升记忆效率。
FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory
- 模仿人类记忆的衰减机制，分层动态调整信息保留
- 多轮对话任务中减少45%存储量，推理更准确
- 适合需要长期记忆与高效管理的智能体系统
将大语言模型部署为自主智能体时，面临关键的记忆限制：缺乏选择性遗忘机制，导致在上下文边界出现灾难性遗忘或内部信息过载。人类记忆通过自适应衰减实现保留与遗忘的平衡，而当前AI系统仅采用二元保留策略，非全保留即全丢失。本文提出FadeMem，一种受生物记忆启发的智能体记忆架构，引入主动遗忘机制，模拟人类认知效率。该架构采用双层记忆层次，对不同信息实施差异化的衰减速率，其保留程度由语义相关性、访问频率和时间模式共同调节。通过大模型引导的冲突消解与智能记忆融合，系统可整合相关信息，同时使无关细节自然褪去。在多会话对话、LoCoMo及LTI-Bench测试中，该方法显著提升多跳推理与检索能力，存储量降低45%，验证了生物启发式遗忘在智能体记忆系统中的有效性。
原文摘要 · Abstract (English)
Large language models deployed as autonomous agents face critical memory limitations, lacking selective forgetting mechanisms that lead to either catastrophic forgetting at context boundaries or information overload within them. While human memory naturally balances retention and forgetting through adaptive decay processes, current AI systems employ binary retention strategies that preserve everything or lose it entirely. We propose FadeMem, a biologically-inspired agent memory architecture that incorporates active forgetting mechanisms mirroring human cognitive efficiency. FadeMem implements differential decay rates across a dual-layer memory hierarchy, where retention is governed by adaptive exponential decay functions modulated by semantic relevance, access frequency, and temporal patterns. Through LLM-guided conflict resolution and intelligent memory fusion, our system consolidates related information while allowing irrelevant details to fade. Experiments on Multi-Session Chat, LoCoMo, and LTI-Bench demonstrate superior multi-hop reasoning and retrieval with 45\% storage reduction, validating the effectiveness of biologically-inspired forgetting in agent memory systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。