{
  "id": 3228,
  "url": "https://arxiv.org/abs/2606.04051v1",
  "title": "RUBAS: Rubric-Based Reinforcement Learning for Agent Safety",
  "summary": "The evolution of LLMs into tool-enabled agents creates a new class of safety challenges associated with real-world execution rather than simple text generation. Existing alignment methods often rely on coarse refusal signals or static supervision, making it difficult to balance safety with useful tool execution across diverse agentic risks. We introduce RUBAS, a rubric-based reinforcement learning framework for agent safety. RUBAS decomposes agent behavior into four dimensions: tool-use safety, ",
  "authors": "Xian Qi Loye, Qinglin Su, Zhexin Zhang, Shiyao Cui, Qi Zhu, Fei Mi et al.",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-02T09:02:14.000Z",
  "fetched_at": "2026-07-14T16:30:05.531Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3228",
  "original_url": "https://arxiv.org/abs/2606.04051v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}