{
  "id": 11588,
  "url": "https://arxiv.org/abs/2607.15263v1",
  "title": "Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents",
  "summary": "Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testing, and CTF completion. Such measurements are useful but incomplete: in operational security, every reasoning step, tool call, telemetry query, and enrichment request consumes budget. We evaluate language-model security agents through this cost-success lens on offensive Cybench challenges and defensive Splunk BOTS v1 in",
  "authors": "Paul Kassianik, Blaine Nelson, Yaron Singer",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-16T17:54:47.000Z",
  "fetched_at": "2026-07-18T05:10:55.931Z",
  "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/11588",
  "original_url": "https://arxiv.org/abs/2607.15263v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}