为长期运行的AI代理设计状态连续性内核，防止状态被错误覆盖或越权修改。
Beyond Memory: A Transactional Continuity Kernel for Long-Lived AI Agents
- 通过事务化机制分离状态评估与激活，确保变更安全
- 在超过550万次状态转移中零违规，验证协议可靠性
- 适合需要高可信状态管理的长期智能体系统
持久化AI代理在长时间跨度中积累版本化状态，但仅靠存储保留无法确定权威状态。缺乏显式控制平面时，模型、工具和后台工作者的未经中介更新可能导致过期覆盖、未审计暴露和自我授权权限提升。我们认为代理状态治理是一个基础设施激活问题，将连续性定义为一条不间断且经授权的分支头接受序列。我们提出连续性内核（CK），一种激活契约，将未提交候选评估与原子状态激活解耦。非信任组件可针对确切前驱头或特定缺失状态提出类型化变更。一次简短激活事务重新验证所有权、前状态权限、新鲜度及效果唯一性，记录单一稳定处置结果（提交、拒绝、隔离或推迟）。仅提交操作会原子性推进分支头，并安装完整接受单元（状态、权限、谱系、效果、结果及凭证）。一个有界可执行模型在2,808,230个可达状态和5,526,474次状态变更转移中验证该协议，未发现任何不变量违反。
原文摘要 · Abstract (English)
Persistent AI agents accumulate versioned state across long horizons, but storage retention alone does not identify authoritative state. Without an explicit control plane, unmediated updates by models, tools, and background workers risk stale overwrites, un-audited exposures, and self-authorizing privilege escalation. We argue that agent state governance is an infrastructural activation problem, defining continuity as an unbroken, authorized lineage of accepted branch heads. We present the Continuity Kernel (CK), an activation contract that decouples off-commit candidate evaluation from atomic state activation. Untrusted components propose typed changes against an exact predecessor head or typed absence. A short activation transaction revalidates ownership, pre-state authority, freshness, and effect uniqueness, recording one stable disposition (Commit, Reject, Quarantine, or Defer). Only Commit atomically advances the branch head and installs the complete accepted unit (state, authority, lineage, effects, outcome, and receipt). A bounded executable model verifies the protocol across 2,808,230 reachable states and 5,526,474 state-changing transitions with zero invariant violations.
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。