系统性梳理长期运行智能体的状态管理与治理机制
Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents
- 从六维维度分析持久状态的特性，构建系统化评估框架
- 435篇文献中状态治理研究薄弱，侧重积累与检索而非回收与审计
- 提出AOEP-v0评估协议，强调状态更新与恢复能力而非仅答案质量
持续运行的智能体其未来行为依赖于跨交互累积的持久状态。我们将其视为持久状态系统：操作系统包含可检索的记忆、任务日志、权限凭证、承诺记录、来源追溯与审计日志、共享状态、触发条件及与这些记录关联的外部效应。本综述通过六个诊断维度（权威性、作用范围、可变性、来源追溯、可恢复性、可操作性）分析每项状态，并依据状态的生命周期——写入、验证、组织、检索、执行、更新、遗忘、审计、必要时回滚——梳理文献。基于对435篇论文构成的编码语料库的分析（视为范围地图而非全面普查），研究更集中于状态的积累与检索，而对治理、恢复或放弃的关注不足。为此，我们引入始终在线评估协议（AOEP-v0），通过评分状态变更与恢复义务来具体化治理要求，而非仅关注回答质量。该议程将持续运行智能体与数据库、分布式系统、形式化方法、能力安全及机器遗忘等领域相连接。
原文摘要 · Abstract (English)
Always-on agents are systems whose future behavior depends on durable state accumulated across earlier interactions. We treat them as persistent-state systems: the operative system includes retrievable memories, but also task ledgers, permissions, credentials, commitments, provenance and audit records, shared state, trigger conditions, and externally committed effects linked to those records. The survey reads the literature through six diagnostic axes for each state item, authority, scope, mutability, provenance, recoverability, and actionability, and through a lifecycle in which state is written, validated, organized, retrieved, acted upon, updated, forgotten, audited, and sometimes rolled back. Across a 435-work coded corpus, treated as a scoped map rather than an exhaustive census, the literature concentrates more heavily on accumulating and retrieving state than on governing, recovering, or relinquishing it. We therefore introduce the Always-On Evaluation Protocol (AOEP-v0), a pilot evaluation contract that makes these governance requirements concrete by scoring state mutation and recovery obligations rather than answer quality alone. The resulting agenda connects always-on agents to databases, distributed systems, formal methods, capability security, and machine unlearning.
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。