一篇很扎实的综述，把LLM智能体“一直在线”带来的状态管理问题系统化了。有435篇论文支撑，还提出了自己的评估协议AOEP-v0，适合想深入理解智能体持久化设计的读者。
该综述聚焦于“永远在线”的LLM智能体，将其视为持久状态系统，涵盖可检索记忆、任务账本、权限、凭证等。论文提出了六个诊断轴（权威性、范围、可变性、来源、可恢复性、可操作性）和生命周期（写入、验证、组织、检索、行动、更新、遗忘、审计、回滚）。基于435篇论文的编码语料库，发现当前研究集中在状态积累与检索，而忽视治理、恢复与放弃。为此，作者引入了Always-On Evaluation Protocol（AOEP-v0），一种通过评分状态突变和恢复义务来测试治理需求的评估合同。该议程将永远在线智能体与数据库、分布式系统、形式化方法、能力安全和机器遗忘等领域联系起来。
Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents
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.