TLDR
AI Agent 能进行事务处理吗？我们认为必须：随着多 Agent 系统（MAS）越来越多地编写代码、部署基础设施、修改数据库并调用 Web 服务，丢失更新或读取过期数据可能带来灾难性后果。尽管 MAS 日益并行执行计划，但当前编排器并不追踪 Agent 读写的数据状态。因此，即使在简单的编码任务中也会出现并发异常。我们将 MAS 协调视为数据管理问题，并提出用状态足迹来描述 Agent：即它们在各自本地上下文和全局状态中读写的状态。Can AI agents transact? We argue that they must: as multi-agent systems (MASs) increasingly write code, deploy infrastructure, modify databases, and call web services, lost updates or stale reads can be catastrophic. Although MASs increasingly execute plans in parallel, current orchestrators do not track the state that agents read and write. As a result, concurrency anomalies manifest even in simple coding tasks. We frame MAS coordination as a data management problem and propose to describe agents by their state footprint: the state they read and write across their own local context and state,