解决大模型长期记忆中的时间错位与信息滞后问题。
MemSIF: From Structured Interactions to Dual-Track Fact Memory for LLM Agents
- 将交互数据分为主题段落和事件轨迹，保持上下文连贯性。
- 双轨记忆机制：核心事实稳定存储，动态事实按需生成并复用。
- 在多个基准上提升2.87%至8.79%，适合长期交互任务的智能体。
长期记忆对长时交互的大型语言模型智能体至关重要。然而，现有记忆系统存在两大持续性偏差：时间-结构错位（TSM）与延迟效用显现（DUM）。TSM表现为时间接近未必主题相关，DUM则指写入时的重要性无法预测未来查询价值。为此，我们提出MemSIF（带结构化交互与事实的记忆框架），包含结构化交互记忆与双轨事实记忆。前者将原始交互划分为保留局部主题一致性的主题段落，以及维持跨时间事件连续性的事件轨迹；后者采用双轨机制：核心事实记忆在写入时基于模式固化稳定信息，活跃事实记忆按需生成，并优先保留多源支持与高频查询的事实以促进复用。在LoCoMo与LongMemEval-S上的实验表明，所有五种骨干模型下MemSIF均取得最高总准确率，在LoCoMo上优于最强基线2.29%-8.79%，在LongMemEval-S上提升2.87%-6.15%。结果验证了结合结构化交互记忆与双轨事实记忆可有效缓解TSM与DUM。代码已开源：https://github.com/luoyufeihaha/MemSIF。
原文摘要 · Abstract (English)
Long-term memory is critical for LLM agents operating over long-horizon interactions. However, several persistent limitations of existing memory systems can be traced to two recurring misalignment patterns in long-term interaction settings: Temporal-Structural Misalignment (TSM) and Delayed Utility Manifestation (DUM). TSM arises when temporal proximity does not reliably align with topical or event-level relatedness, whereas DUM arises when write-time salience does not reliably predict future query utility. To mitigate these misalignment patterns, we propose MemSIF (Memory with Structured Interactions and Facts), a structured interaction-to-fact memory framework. Structured Interaction Memory organizes raw interactions into Topical Segments that preserve local topical coherence and Event Trajectories that maintain cross-time event continuity. Dual-Track Fact Memory uses two complementary tracks: CoreFact memory consolidates stable, schema-guided information at write time, whereas ActiveFact memory forms facts on demand and promotes those supported by multiple historical sources and recurring query demand for reuse. Experiments on LoCoMo and LongMemEval-S across five backbone LLMs show that MemSIF achieves the highest Total ACC in all settings, outperforming the strongest baseline by 2.29%-8.79% on LoCoMo and 2.87%-6.15% on LongMemEval-S. These results support the effectiveness of combining Structured Interaction Memory with Dual-Track Fact Memory to mitigate TSM and DUM. Code is available at https://github.com/luoyufeihaha/MemSIF.
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。