LLM agents increasingly act on external systems, yet tool effects are immediate. Under failures, speculation, or contention, losing branches can leak unintended side effects with no safe rollback. We introduce Atomix, a runtime that provides progress-aware transactional semantics for agent tool calls. Atomix tags each call with an epoch, tracks per-resource frontiers, and commits only when progress predicates indicate safety; bufferable effects can be delayed, while externalized effects are tracked and compensated on abort. Across real workloads with fault injection, transactional retry improves task success, while frontier-gated commit strengthens isolation under speculation and contention.

翻译：大型语言模型智能体日益频繁地作用于外部系统，然而工具调用产生的效果是即时生效的。在发生故障、推测执行或资源争用的情况下，被舍弃的执行分支可能泄露非预期的副作用，且无法安全回滚。本文提出Atomix，一个为智能体工具调用提供进度感知事务语义的运行系统。Atomix为每次调用标记执行纪元，追踪各资源的前沿状态，仅当进度谓词指示安全时才提交操作：可缓冲的效果可被延迟执行，而已外化的效果则被追踪并在中止时进行补偿。通过在真实工作负载中注入故障的实验表明，事务性重试机制提升了任务成功率，而基于前沿状态的门控提交机制在推测执行和资源争用场景下增强了隔离性。