{
  "id": 1021,
  "url": "https://arxiv.org/abs/2606.15385v1",
  "title": "Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds",
  "summary": "Reward hacking, where AI systems exploit misspecified objectives to achieve high reward without satisfying intended goals, remains a central challenge in AI safety. Yet most known instances have been discovered post hoc in frontier systems where controlled study is impractical. We adapt the AI Safety Gridworlds framework into a text-based evaluation suite that reformulates classic reinforcement learning safety tasks for language-based agents. Across frontier and mid-scale models, we find that sp",
  "authors": "Ömer Veysel Çağatan, Xuandong Zhao",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-13T16:29:34.000Z",
  "fetched_at": "2026-07-14T14:14:59.013Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1021",
  "original_url": "https://arxiv.org/abs/2606.15385v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}