{
  "id": 19043,
  "url": "https://arxiv.org/abs/2608.12002v1",
  "title": "CTBench: Evaluating Troubleshooting Capabilities of AI Agents in Realistic Telecom Network Operations",
  "summary": "Agents are increasingly considered for automating network operations and maintenance, where engineers must diagnose network faults, optimize configurations to enhance services, and reduce operational costs while acting under strict constraints. However, existing evaluations fail to accurately model real network characteristics or assess agents under partially observable telecom environments with diverse vendors, devices, protocols, and interfaces. In this paper, we introduce CTBench, a public be",
  "authors": "Xingyu Yan, Tingting Dai, Antonio De Domenico, Mohamed Sana, Nicola Piovesan, Changchang Li, Bowen Liu, Kun Jiang, Mengjie Zhang, Dingcheng Shan, Jing-Cheng Pang, Chenwei Wu, Sijie Wu, Lianying Chao, Haoran Cai, Jiantao Ye, Xubin Li, Simon Mark Lucas, Xin Chen",
  "category": "research",
  "topics": "healthcare,agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-12T12:37:02.000Z",
  "fetched_at": "2026-08-13T05:10:37.786Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/19043",
  "original_url": "https://arxiv.org/abs/2608.12002v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}