arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.12874cs.CL
收藏

用于长程多方对话记忆的时序证据森林

Temporal Evidence Forests for Long-Horizon Multi-Party Conversational Memory

School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院);Alibaba Group(阿里巴巴集团)

Junyou Guo, Chongyang Tao, Yan He, Yong Wang, Shuai Ma

AI总结:

针对现有时序记忆框架未利用时序结构恢复证据与重构事件进程的局限,提出基于时序结构的记忆框架T-Mem,经实验验证其在多类基准上优于竞争性框架。

摘要:

长期记忆已被广泛应用于基于大语言模型(LLM)的智能体,以支持持续交互和个性化辅助。然而,长期多方交互会积累大量更详细的信息,决策会被反复更新,状态会随参与者和交互阶段发生演变。因此,时序结构对于追踪此类记忆至关重要:相关信息常密集出现在短时间间隔内,而不同状态间的转换则由严格的时序顺序锚定。现有的时序感知记忆框架主要将时间作为元数据存储,或利用时序信号指导对预先构建的记忆结构的检索,未将时序结构同时用于恢复局部集中的证据并重构其完整事件进程。为解决这些局限,我们提出T-Mem,一种基于时序结构的记忆框架,它通过两种时序机制存储交互并组织与查询相关的证据:时序证据发现利用相关消息的局部集中性恢复被忽略的证据;时序记忆结构化对随时间变化的状态转换和支撑关系进行建模,并压缩所得森林中的低信息跨度;证据森林线性化则将结构化证据序列化以用于生成答案。在两个长期多方记忆基准上的实验表明,T-Mem在各类LLM、参数设置、领域及查询类型中均始终优于竞争性记忆框架。

英文摘要:

Long-term memory has been widely adopted in LLM-based agents to support persistent interaction and personalized assistance. Long-term multi-party interactions, however, accumulate substantially more detailed information, with decisions repeatedly updated and states evolving across participants and interaction stages. Temporal structure is therefore crucial for tracing such memories: relevant information often appears densely within short intervals, while transitions among different states are anchored by a strict temporal order. Existing temporally aware memory frameworks primarily store time as metadata or use temporal signals to guide retrieval over preconstructed memory structures, without using temporal structure to both recover locally concentrated evidence and reconstruct its complete event progression. To address these limitations, we propose T-Mem, a temporal-structure-based memory framework that preserves interactions and organizes query-relevant evidence through two temporal mechanisms. Temporal Evidence Discovery exploits the local concentration of related messages to recover overlooked evidence, while Temporal Memory Structuring models state transitions and supporting relations over time and compresses low-information spans within the resulting forest. Evidence Forest Linearization then serializes the structured evidence for answer generation. Experiments on two long-term multi-party memory benchmarks demonstrate that T-Mem consistently outperforms competitive memory frameworks across LLMs, parameter settings, domains, and query types.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑