分层记忆架构提升大模型长对话稳定性
Multi-Layered Memory Architectures for LLM Agents: An Experimental Evaluation of Long-Term Context Retention
- 分三层次管理对话记忆，自适应检索与正则化控制漂移
- 六周期记忆保留率达56.9%，虚假记忆率降至5.1%
- 适合长程对话、需稳定记忆的智能助手场景
长时对话系统面临语义漂移和记忆不稳问题。本文提出多层记忆框架，将对话历史分解为工作记忆、情景记忆和语义记忆三层，结合自适应检索门控与保留正则化。该架构在跨会话中控制语义漂移，同时保持上下文增长有界且计算高效。在LOCOMO、LOCCO和LoCoMo数据集上的实验表明，性能显著提升：成功率达46.85%，整体F1为0.618，多跳任务F1达0.594，六周期记忆保留率为56.90%，虚假记忆率降低至5.1%，上下文使用量减少至58.40%。结果验证了在有限上下文预算下，长期记忆与推理稳定性均得到增强。
原文摘要 · Abstract (English)
Long-horizon dialogue systems suffer from semanticdrift and unstable memory retention across extended sessions. This paper presents a Multi-Layer Memory Framework that decomposes dialogue history into working, episodic, and semantic layers with adaptive retrieval gating and retention regularization. The architecture controls cross-session drift while maintaining bounded context growth and computational efficiency. Experiments on LOCOMO, LOCCO, and LoCoMo show improved performance, achieving 46.85 Success Rate, 0.618 overall F1 with 0.594 multi-hop F1, and 56.90% six-period retention while reducing false memory rate to 5.1% and context usage to 58.40%. Results confirm enhanced long-term retention and reasoning stability under constrained context budgets.
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。