提出自适应遗忘机制，让AI对话系统在长期对话中保持记忆精准与高效。
Novel Memory Forgetting Techniques for Autonomous AI Agents: Balancing Relevance and Efficiency
- 基于相关性评分与约束优化，动态调节记忆保留
- 长对话下F1超过0.583，虚假记忆率显著降低
- 适合需要持久记忆的智能对话系统研发
长时对话代理需持久记忆以实现连贯推理，但无控制的记忆积累会导致时间衰减与虚假记忆传播。基准测试显示，LOCOMO和LOCCO在多个阶段性能从0.455降至0.05，MultiWOZ在持续保留下准确率达78.2%，虚假记忆率为6.8%。本文提出一种自适应预算遗忘框架，通过相关性引导评分与有界优化调控记忆。该方法融合时效性、频率与语义对齐，确保在有限上下文下的稳定性。对比分析表明，该方法在长时对话中将F1提升至0.583以上，增强记忆一致性，减少虚假记忆行为，且不增加上下文开销。结果证实，结构化遗忘可在防止记忆无限增长的同时维持推理性能。
原文摘要 · Abstract (English)
Long-horizon conversational agents require persistent memory for coherent reasoning, yet uncontrolled accumulation causes temporal decay and false memory propagation. Benchmarks such as LOCOMO and LOCCO report performance degradation from 0.455 to 0.05 across stages, while MultiWOZ shows 78.2% accuracy with 6.8% false memory rate under persistent retention. This work introduces an adaptive budgeted forgetting framework that regulates memory through relevanceguided scoring and bounded optimization. The approach integrates recency, frequency, and semantic alignment to maintain stability under constrained context. Comparative analysis demonstrates improved long-horizon F1 beyond 0.583 baseline levels, higher retention consistency, and reduced false memory behavior without increasing context usage. These findings confirm that structured forgetting preserves reasoning performance while preventing unbounded memory growth in extended conversational settings.
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。