Skip to content
Sagan

Paper

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

Unreadunread

AI summary

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.