让对话智能体主动思考记忆，而非被动检索。
MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents
- 将记忆组织成可导航的关联图谱，支持多步推理
- 在长对话任务中达92.98分，主动记忆测试显著领先
- 适合需要深度记忆推理的复杂对话系统研究
现有对话智能体的记忆系统普遍遵循‘记忆即工具’范式，单次查询仅触发扁平片段的一次性检索，存在调用被动、推理与检索分离、检索结果与导航需求结构不匹配等问题。本文提出MemCog——一种将记忆作为认知过程一部分的‘记忆即认知’系统。该系统将用户知识组织为可导航的记忆存储，构建跨维度导航接口以支持多步推理驱动的遍历，并引入主动推理协议，使智能体能从对话上下文中自发启动记忆探索。此外，我们构建了首个评估主动记忆触发的基准数据集ProactiveMemBench。实验表明，MemCog在被动问答基准上达到顶尖水平（LoCoMo 92.98，LongMemEval 95.8），并在主动记忆测试中显著超越基线，验证了‘记忆即认知’的优势。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。