提出双进程记忆系统，让大模型能像人一样自我演化。
Memory Beyond Recall: A Dual-Process Cognitive Memory System for Self-Evolving LLM Agents
- 用双进程架构区分快速记录与深度思考，分层组织记忆
- 在跨会话推理任务上提升最多达5.20分，显著优于传统方法
- 适合需要长期身份演化的智能体，如个性化助手
大语言模型的长期记忆不仅是准确召回信息，更涉及信念更新、因果关联和跨领域抽象。现有记忆系统将这些能力压缩为单一检索接口，难以处理用户行为演变等隐式个性化需求。本文提出DCPM，基于认知能力层级重构记忆：从原始输入、原子事实，到时序信念轨迹与身份认同，再到领域模式、潜在意图和跨域规律。该层级由双进程机制驱动：同步的白天写入器（System1）以双向链表记录信念迭代；异步的夜间引擎（System2）则生成模式、推断意图，并提取跨域冲突形成高层核心模式。在LongMemEval、PersonaMem和PersonaMem-v2测试中，开启System2在需隐式跨会话推理的任务上表现最优（最高提升5.20分），而在片段召回任务上增益最小，符合架构预期。
原文摘要 · Abstract (English)
Long-term memory for an LLM agent is more than retrieving the right passage at the right time. Current memory systems collapse belief revision, causal coupling, and cross-domain abstraction into a single retrieval surface tuned for surface recall, and consequently struggle on implicit personalisation that requires reasoning over how a user has evolved. We propose DCPM, which reorganises agent memory along a cognitive capability hierarchy ascending from raw inputs and atomic facts, through diachronic belief trajectories and identity, to domain schemas, latent intentions and cross-domain patterns. The hierarchy is driven by two processes inheriting the architectural split of dual-process theory: a synchronous daytime writer (System1) that records belief revisions as doubly linked supersedes chains, and an asynchronous nighttime engine (System2) that induces schemas and intentions and sweeps for cross-domain collisions abstracted into higher-level core schemas. On LongMemEval, PersonaMem and PersonaMem-v2, enabling System2 contributes most where the benchmark rewards implicit cross-session inference (up to +5.20 on PersonaMem-v2) and least on span recall, matching the architectural prediction.
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。