{
  "id": 4770760,
  "title": "GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM Reasoning",
  "url": "https://urgent.news/2026/08/31/gmts-gradient-magnitude-based-token-selection-improves-rlvr-training",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-31T11:41:11.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.30632v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Reinforcement learning (RL), particularly RL with Verifiable Rewards (RLVR), has recently emerged as a central paradigm for enhancing large language models' (LLMs) reasoning abilities, demonstrating remarkable effectiveness across reasoning tasks. Recent studies suggest that high-entropy tokens play an exceptionally important role in model training, since training with only the highest 20%…",
  "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."
}