Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows
AI 摘要
Atomix为LLM Agent工具调用提供事务性语义,提升可靠性和安全性。
主要贡献
- 提出Atomix运行时,支持agent工具调用的事务性语义
- 引入epoch标记、资源边界追踪和进度谓词机制
- 设计可缓冲和外部化效果的处理策略,支持回滚和补偿
方法论
设计Atomix运行时,通过跟踪资源状态和进度,在安全时提交工具调用,失败时回滚。
原文摘要
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.