{
  "id": 4746,
  "url": "https://arxiv.org/abs/2605.07505v1",
  "title": "LiteGUI: Distilling Compact GUI Agents with Reinforcement Learning",
  "summary": "Developing lightweight, on-device vision-language GUI agents is essential for efficient cross-platform automated interaction. However, current on-device agents are constrained by limited model capacity, and further performance improvements remain urgently needed. Traditional Supervised Fine-Tuning (SFT) for small-scale models often leads to overfitting, catastrophic forgetting and policy rigidity, and thus fails to fully address these challenges. In this work, we propose a novel SFT-free trainin",
  "authors": "Yubin Wu, Zicheng Cai, Liping Ning, Hua Wang, Zhi Chen, Yaohua Tang et al.",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-08T09:38:29.000Z",
  "fetched_at": "2026-07-14T16:31:12.747Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4746",
  "original_url": "https://arxiv.org/abs/2605.07505v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}