超越记忆：面向长生命周期智能体的事务连续性内核
Beyond Memory: A Transactional Continuity Kernel for Long-Lived AI Agents
浏览论文内容
中文总结 AI 辅助
针对长生命周期AI智能体的状态治理风险，提出连续性内核（CK）激活合约，通过解耦候选评估与状态激活，验证协议在大规模状态空间上无不变量违反。
中文摘要 AI 辅助
持久AI智能体在长周期内积累带版本的状态，但仅存储保留无法确定权威状态。若无显式控制平面，模型、工具及后台工作进程的无中介更新存在过时覆盖、未审计暴露、自授权权限提升的风险。本文提出智能体状态治理是基础设施激活问题，将连续性定义为已接受分支头的未中断授权谱系。我们提出连续性内核（CK），这是一种激活合约，将提交外的候选评估与原子状态激活解耦。不可信组件针对精确前驱头或类型缺失提出类型化变更。简短激活事务会重新验证所有权、预状态权限、新鲜度及效果唯一性，记录稳定处置结果（提交、拒绝、隔离或推迟）。仅提交操作会原子推进分支头并安装完整接受单元（状态、权限、谱系、效果、结果及收据）。有界可执行模型在2808230个可达状态及5526474个状态变更转换上验证了该协议，未出现任何不变量违反。
英文摘要
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.
