当工具调用成功但工作流失败：智能体-工具边界处的异常
When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool Boundary
浏览论文内容
中文总结 AI 辅助
本研究提出效果历史模型，识别八种智能体-工具边界外部效果异常，分析MCP接口能力不足，倡导可重用事务契约。
中文摘要 AI 辅助
AI智能体越来越多地执行长时间运行的工作流，这些工作流通过独立提供的工具将效果外部化。在重试、推测执行、并发和部分失败的情况下，所产生的外部状态可能与工作流预期的解析结果不一致：所需效果可能缺失或重复，已中止的效果可能仍然存在，已提交的效果可能依赖于后来被撤回的临时状态。高级事务模型解决了相关的失败，但假设底层操作暴露了它们所依赖的语义：效果是否发生，是否可以补偿、暂存或安全地重新排序。共享的智能体-工具接口通常不提供这些语义。我们贡献了一个效果历史模型，将外部世界中的事件与运行时对它们的观察分开，以及一个包含八种重复出现的外部效果异常的目录。从该目录中，我们推导出在一般情况下排除每种异常所需的边界能力，以及四个仅靠黑盒工具调用无法提供一般保证的点。然后，我们询问在广泛使用的共享工具接口中，这些能力有多少是可表达的，测量了在注册的模型上下文协议（MCP）服务器暴露的98,291个工具中标准注释词汇的使用情况。这些字段被广泛使用，但仅提供粗略的调用级提示，并且所需的能力没有一个是完全可表达的。这些结果激励在工具边界处使用可重用的事务性契约。
英文摘要
AI agents increasingly execute long-running workflows that externalize effects through independently supplied tools. Under retries, speculative execution, concurrency, and partial failures, the resulting external state may be inconsistent with the workflow's intended resolution: required effects may be missing or duplicated, aborted effects may survive, and committed effects may depend on provisional state that is later withdrawn. Advanced transaction models address related failures, but assume that lower-level operations expose the semantics they depend on: whether an effect occurred, whether it can be compensated, staged, or safely reordered. Shared agent-tool interfaces usually do not. We contribute an effect-history model that separates events in the external world from the runtime's observations of them, and a catalog of eight recurring external-effect anomalies. From the catalog we derive the boundary capabilities required to exclude each anomaly in general, and four points where black-box tool invocation alone cannot provide a general guarantee. We then ask how much of this is expressible in a widely used shared tool interface, measuring the use of the standard annotation vocabulary across 98,291 tools exposed by registered Model Context Protocol (MCP) servers. The fields are widely emitted but provide only coarse call-level hints, and none of the required capabilities is fully expressible. These results motivate reusable transactional contracts at the tool boundary.
发表机构
- AVIV Group（AVIV集团）
机构由 AI 辅助整理，请以论文原文为准。
