Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents

본문 미리보기

arXiv:2606.07904v1 Announce Type: new Abstract: Tool-augmented large language model agents increasingly rely on external APIs, but standard tool schemas describe how to call a tool, not when the tool is causally appropriate or what task state it produces. Causal tool filtering addresses this gap by using lightweight contracts that specify each tool's preconditions, effects, risk level, and cost. However, manually writing and maintaining such contracts does not scale to large or changing tool ec