让大模型代理任务可靠执行，避免并发冲突和部分失败。
Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows
- 用带进度感知的事务机制记录操作，确保原子提交。
- 在无早期冲突工作残留时才提交，杜绝脏写与漏发。
- 适合高可靠性需求的自动化流程，如金融或医疗代理。
大型语言模型代理通过工具执行多步工作流并改变外部状态。现有编排器常以工具返回作为结算触发点，导致故障、推测执行及并发代理可能留下部分影响、丢失分支残留、过期写入或不可逆调用。正确结算需要两个关键信息：哪些效果必须一同提交，以及更早的冲突工作是否已彻底结束。Atomix 显式分离这两个要素，采用进度感知事务机制：运行时记录读取和效果，当其行为足迹完整时封存事务，并在每个资源的前缘确认无早期冲突工作可再到达后才提交。提交即为最终结算：释放缓冲效果，接受可逆外部操作为最终状态，允许不可逆操作离场。回滚则抑制未释放效果，并尽可能补偿已外化的可逆效果。在典型代理负载下，该方案提升了注入故障下的干净恢复能力，隔离竞争与推测性工作，并防止正确分类的不可逆操作泄漏；微基准测试显示相对于工具延迟，封装开销仅为微秒级。
原文摘要 · Abstract (English)
LLM agents execute multi-step workflows that mutate external state through tools. Common orchestrators treat tool return as the settlement trigger, so faults, speculation, and concurrent agents can leave partial effects, losing-branch residue, stale writes, or irreversible sends. Correct settlement needs two facts that retries, checkpoint replay, locks, and compensation each conflate: which effects must settle together, and when earlier conflicting work is exhausted. Atomix makes this split explicit with progress-aware transactions. The runtime records reads and effects during execution, seals a transaction when its footprint is complete, and commits only after per-resource frontiers show that no earlier conflicting work can still arrive. Commit is final settlement: Atomix releases bufferable effects, accepts reversible external effects as final, and lets irreversible effects leave the gate. Abort suppresses unreleased effects and compensates externalized reversible effects where possible. On representative agent workloads, this composition improves clean recovery under injected faults, isolates contending and speculative work, and prevents correctly classified irreversible actions from leaking; microbenchmarks show microsecond-scale wrapper overhead relative to tool latency.
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。