{
  "id": 8148345,
  "title": "MATCH: Model-Aware Tool Learning with Curriculum Scheduling and Hierarchically Gated Rewards",
  "url": "https://urgent.news/2026/09/17/match-model-aware-tool-learning-with-curriculum-scheduling-and",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-17T11:40:26.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.20082v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "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…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}