arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.04885cs.AI
收藏

面向流式对话的主动记忆

Proactive Memory for Ad-Hoc Recall over Streaming Dialogues

Department of Computing（计算系）；The Hong Kong Polytechnic University（香港理工大学）；The School of Computer Science and Technology（计算机科学与技术学院）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））

Bingbing Wang, Jing Li, Ruifeng Xu

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出ProStream框架，通过分层结构和多粒度蒸馏实现流式对话中的主动记忆召回，解决记忆 fidelity 与效率的矛盾，提升推理精度并降低延迟。

摘要：

现实中的对话通常以无限流的形式展开，因此需要有限状态内存机制在无限时间范围内运作。然而，现有读-思内存机制与这种设置根本不符，因为它们无法在流式展开时支持随机记忆召回。为此，我们引入STEM-Bench，首个用于流式内存评估的基准，包含超过14000个对话流问答对，评估感知保真度、时间推理和全局意识在无限时间范围内的表现。初步分析表明存在关键的保真度-效率矛盾：基于检索的方法使用片段上下文，而全上下文模型导致无界延迟。为解决此问题，我们提出ProStream，一种基于分层结构的主动内存框架，通过在连续流上进行推理实现按需记忆召回，并采用自适应时空优化动态优化保留基于预期效用。它在不牺牲推理保真度的情况下实现了有限的知识状态，以降低推理延迟。实验表明，ProStream在推理保真度方面优于先前基线，同时比全上下文替代方案保持显著更低的延迟。

英文摘要：

Real-world dialogue usually unfolds as an infinite stream. It thus requires bounded-state memory mechanisms to operate within an infinite horizon. However, existing read-then-think memory is fundamentally misaligned with this setting, as it cannot support ad-hoc memory recall while streams unfold. To explore this challenge, we introduce \textbf{STEM-Bench}, the first benchmark for \textbf{ST}reaming \textbf{E}valuation of \textbf{M}emory. It comprises over 14K QA pairs in dialogue streams that assess perception fidelity, temporal reasoning, and global awareness under infinite-horizon constraints. The preliminary analysis on STEM-Bench indicates a critical textit{fidelity-efficiency dilemma}: retrieval-based methods use fragment context, while full-context models incur unbounded latency. To resolve this, we propose \textbf{ProStream}, a proactive memory framework for streaming dialogues built on a hierarchical structure. It enables ad-hoc memory recall on demand by reasoning over continuous streams with multi-granular distillation. Moreover, it employs Adaptive Spatiotemporal Optimization to dynamically optimize retention based on expected utility. It enables a bounded knowledge state for lower inference latency without sacrificing reasoning fidelity. Experiments show ProStream delivers higher reasoning fidelity than prior baselines while maintaining substantially lower latency than full-context alternatives.

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。

↑