arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2506.08098cs.AI
收藏

Cognitive Weave:利用时空共振图综合抽象知识

Cognitive Weave: Synthesizing Abstracted Knowledge with a Spatio-Temporal Resonance Graph

University of Southern California(南加州大学);WorkOnward, Inc(WorkOnward公司);Yeshiva University(耶鲁大学);IEEE Senior Member(IEEE高级会员);Northeastern University(东北大学)

Akash Vishwakarma, Hojin Lee, Mohith Suresh, Priyam Shankar Sharma, Rahul Vishwakarma, Sparsh Gupta, Yuvraj Anupam Chauhan

AI总结:

本文提出 Cognitive Weave 记忆框架,利用多层 STRG 管理洞见粒子并自主综合高层知识,实验显示其长程规划、问答和多会话对话性能显著提升。

摘要:

基于大语言模型(LLM)的强大智能体的出现,要求记忆架构超越单纯的数据存储,实现持续学习、细致推理和动态适应。当前记忆系统往往在结构灵活性、时间感知以及从原始交互数据中综合更高层次洞见的能力方面受制于根本性局限。本文介绍 Cognitive Weave,这是一种围绕多层时空共振图(STRG)构建的新型记忆框架。该图将信息作为语义丰富的洞见粒子(IP)进行管理,并通过专用语义预言机接口(SOI)为其动态补充共振键、指示符和情境印记。这些 IP 通过有类型的关系链相互连接,形成不断演化的知识织锦。Cognitive Weave 的一个关键组成部分是认知精炼过程,这是一种自主机制,包括综合洞见聚合体(IA),即从已识别的相关 IP 簇中提炼出的浓缩、更高层次知识结构。我们给出了全面实验结果,证明 Cognitive Weave 在长程规划任务、不断演化的问答场景以及多会话对话连贯性方面相较现有方法具有显著增强。与最先进基线相比,该系统在任务完成率上实现了显著的34%平均提升,并使平均查询延迟降低42%。此外,本文探讨了此类高级记忆系统固有的伦理考量,讨论了其对 LLM 长期记忆的影响,并概述了有前景的未来研究轨迹。

英文摘要:

The emergence of capable large language model (LLM) based agents necessitates memory architectures that transcend mere data storage, enabling continuous learning, nuanced reasoning, and dynamic adaptation. Current memory systems often grapple with fundamental limitations in structural flexibility, temporal awareness, and the ability to synthesize higher-level insights from raw interaction data. This paper introduces Cognitive Weave, a novel memory framework centered around a multi-layered spatio-temporal resonance graph (STRG). This graph manages information as semantically rich insight particles (IPs), which are dynamically enriched with resonance keys, signifiers, and situational imprints via a dedicated semantic oracle interface (SOI). These IPs are interconnected through typed relational strands, forming an evolving knowledge tapestry. A key component of Cognitive Weave is the cognitive refinement process, an autonomous mechanism that includes the synthesis of insight aggregates (IAs) condensed, higher-level knowledge structures derived from identified clusters of related IPs. We present comprehensive experimental results demonstrating Cognitive Weave's marked enhancement over existing approaches in long-horizon planning tasks, evolving question-answering scenarios, and multi-session dialogue coherence. The system achieves a notable 34% average improvement in task completion rates and a 42% reduction in mean query latency when compared to state-of-the-art baselines. Furthermore, this paper explores the ethical considerations inherent in such advanced memory systems, discusses the implications for long-term memory in LLMs, and outlines promising future research trajectories.

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。

↑