AI 中文总结
本文提出FTA-Mem结构化记忆框架，通过BWS形成情境片段并构建FTA单元，在ES-MemEval等数据集上提升了低密度长期对话的记忆问答性能，实现了证据保留与构建成本的有效权衡。
AI 中文摘要
长期情感支持智能体需要记忆机制来实现跨会话的个性化理解，但情感支持对话往往具有低密度特性：对话轮次信息不完整、证据分散且用户状态随时间演变。现有记忆方法通常依赖固定单元，如轮级笔记或会话摘要，可能丢失细节或引入冗余噪声。本文提出FTA-Mem，一种面向低密度长期对话的结构化记忆框架：该框架采用边界保留窗口分割（BWS）形成连贯情境片段，构建事实-时间-情感记忆单元（FTA单元），联合编码事实内容、时间定位与情感上下文；检索到的单元随后被合成为结构化上下文用于生成回复。在ES-MemEval和LoCoMo上的实验表明，FTA-Mem可提升不同信息密度基准下的长期记忆问答性能：在ES-MemEval上，FTA-Mem取得0.3871的F1值和0.6668的BERTScore；进一步分析显示，情境级FTA构建相比粗糙的会话级或过细的轮次对构建，能更好地平衡证据保留与构建成本，为长期对话记忆提供了有效的粒度权衡方案。
英文摘要
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.
