{
  "id": 7396,
  "url": "https://arxiv.org/abs/2603.13384v3",
  "title": "VulnAgent-R2: Evidence-Calibrated Multi-Agent Auditing for Repository-Level Vulnerability Detection",
  "summary": "Software vulnerabilities often depend on cross-file data flow, build options, framework conventions, and runtime guards, so isolated function classifiers produce fragile and poorly calibrated warnings. Repository-level LLM agents can gather richer evidence, but prior variants under-specify reproducibility, verifier behavior, baseline fairness, and statistical uncertainty. We present VulnAgent-R2, a budget-aware agentic auditing framework with three additional reusable modules: counterfactual evi",
  "authors": "Renwei Meng, Haoyi Wu, Jingming Wang",
  "category": "research",
  "topics": "bias-fairness,agents-autonomy,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-11T04:57:17.000Z",
  "fetched_at": "2026-07-14T16:33:12.390Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/7396",
  "original_url": "https://arxiv.org/abs/2603.13384v3",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}