Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents

Excerpt

arXiv:2610.04375v1 Announce Type: new Abstract: Agents built on large language models (LLMs) build and run software through tool calls. A call reaches its program through several hops, and any hop can change the call without notice. When the changed call fails, the agent retries a correct call, which costs users time and money. Benchmarks and failure analyses do not see the change, because they read the call and its result but not what a hop received. We define intent-execution correspondence (I