{
  "id": 723511,
  "title": "VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies",
  "url": "https://urgent.news/2026/08/12/vakra-evaluating-multi-hop-reasoning-across-apis-and-retrieval-under",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-12T17:27:27.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.12282v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities in isolation. We introduce VAKRA (e\\textbf{V}aluating \\textbf{A}PI and \\textbf{K}nowledge \\textbf{R}etrieval \\textbf{A}gents), a benchmark of over $8{,}000$ executable APIs across $62$ domains with tasks spanning three settings of increasing…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}