MATCH: Model-Aware Tool Learning with Curriculum Scheduling and Hierarchically Gated Rewards
Tool learning enables large language models (LLMs) to use external tools for tasks beyond parametric knowledge. Reinforcement learning can optimize tool-call behavior from feedback, but current methods still face two problems: fixed-threshold curricula can become misaligned with the policy's evolving capability boundary, and additive rewards can leak argument-level credit when the predicted tool…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
