SOURCE-LINKED INTELLIGENCE

MATCH: Model-Aware Tool Learning with Curriculum Scheduling and Hierarchically Gated Rewards

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

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 is wrong. To address these problems, we propose MATCH, a closed-loop framework for model-aware tool learning with curriculum scheduling and hierarchically gated rewards. Model-Aware Curriculum Learning

Read original source ↗ Open in workspace

recordType

paper

region

Global