arXiv：cs.CL· Chang Liu, Junyi Zhao, Shuyi Zhang, Changsheng Ma, Yongfeng Tao, Minqiang Yang, Bin Hu·· 3 小时前AI 评分30
FTA-Mem：面向低密度长期对话的事实-时间-情感锚定记忆框架
FTA-Mem: Fact-Time-Affect Anchored Memory for Low-Density Long-Term Dialogue
AI 导读
FTA-Mem 是一个面向低密度长期对话的结构化记忆框架，通过边界保留窗口分段（BWS）构建情境片段，并建立同时编码事实内容、时间锚定与情感上下文的事实-时间-情感记忆单元（FTA Units），检索后合成结构化上下文用于答案生成。
正文
Abstract:Long-term emotional-support agents require memory mechanisms for personalized understanding across sessions. However, emotional-support dialogue is often low-density: turns are incomplete, evidence is scattered, and user states evolve over time. Existing memory methods usually rely on fixed units, such as turn-level notes or session summaries, which may lose details or introduce redundant noise. We propose FTA-Mem, a structured memory framework for low-density long-term dialogue. FTA-Mem uses Boundary-preserving Window Segmentation (BWS) to form coherent situation fragments, and constructs Fact-Time-Affect Memory Units (FTA Units) that jointly encode factual content, temporal grounding, and affective context. Retrieved units are then synthesized into structured context for answer generation. Experiments on ES-MemEval and LoCoMo show that FTA-Mem improves overall long-term memory question answering across benchmarks with different information-density characteristics. On ES-MemEval, FTA-Mem achieves 0.3871 F1 and 0.6668 BERTScore. Further analysis shows that situation-level FTA construction better balances evidence preservation and construction cost than coarse session-level or overly fine-grained turn-pair construction, providing an effective granularity trade-off for long-term dialogue memory.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2608.16303 [cs.CL] |
| (or arXiv:2608.16303v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2608.16303 arXiv-issued DOI via DataCite |
Submission history
From: Chang Liu [view email]
[v1]
Mon, 17 Aug 2026 09:14:31 UTC (276 KB)
[v2]
Wed, 7 Oct 2026 03:09:21 UTC (276 KB)
来源：arXiv：cs.CL · arxiv.org