arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.28046cs.AIcs.CL
收藏

MemCog: 从记忆即工具到记忆即认知的对话代理

MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents

WeChat, Tencent Inc.(腾讯公司)

Zihan Li, Xingyu Fan, Feifei Li, Wenhui Que

AI总结:

提出MemCog系统,通过可导航记忆存储、跨维度导航接口和主动推理协议,将记忆访问融入推理过程,在被动问答和主动记忆触发基准上达到最优性能。

摘要:

现有的代理记忆系统普遍遵循我们称之为“记忆即工具”的范式,其中单个查询触发对扁平段落列表的一次性检索,存在被动调用、推理-检索解耦以及检索片段与代理导航需求之间的结构不匹配等问题。我们提出MemCog,一个“记忆即认知”系统,使记忆访问成为推理过程的一个组成部分。MemCog将用户知识组织为具有关联链接图的可导航记忆存储,暴露跨维度导航接口以进行多步推理驱动的遍历,并采用主动推理协议,驱动代理从对话上下文中自发启动记忆探索。我们还构建了ProactiveMemBench,这是第一个用于评估主动记忆触发的基准。实验表明,MemCog在被动问答基准上达到了最先进水平(LoCoMo上92.98,LongMemEval上95.8),同时在ProactiveMemBench上大幅超越基线,展示了记忆即认知的优势。

英文摘要:

Existing agent memory systems universally follow what we term a Memory-as-Tool paradigm where a single query triggers one-shot retrieval of flat passage lists, suffering from passive invocation, reasoning-retrieval decoupling, and structural mismatch between retrieved fragments and the agent's navigational needs. We propose MemCog, a Memory-as-Cognition system that makes memory access an integral part of the reasoning process. MemCog organizes user knowledge as Navigable Memory Store with associative link graphs, exposes Cross-Dimensional Navigation Interface for multi-step reasoning-driven traversal, and employs Proactive Reasoning Protocol that drives agents to spontaneously initiate memory exploration from conversational context. We additionally construct ProactiveMemBench, the first benchmark for evaluating proactive memory triggering. Experiments show that MemCog achieves state-of-the-art on passive QA benchmarks (92.98 on LoCoMo, 95.8 on LongMemEval) while substantially outperforming baselines on ProactiveMemBench, demonstrating the advantage of Memory-as-Cognition.

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。

↑