{
  "id": "clasharness",
  "name": "CLASHarness",
  "category": "information",
  "summary": "Google Research benchmark and generator of 600 verifiable multi-agent conflict tasks in computer use: stale sub-agent reports, contradictory instructions, shared locks.",
  "description": "Paper: arXiv 2610.19128 (Oct 2026). Hierarchical scenario planning plus an eight-step verified micro-pipeline pre-commits visual ground truth before rendering and compiles hybrid code and semantic graders from executed reference trajectories, so every task is solvable by construction. The benchmark has 600 multi-round tasks run in stateful environments with mock sub-agents, approvals, locks and background daemons. Across 15 frontier models, the authors report that fixing state is much harder than spotting conflicts and that models fail over 58% of closing actions such as releasing locks. Code Apache-2.0 (Python 3.11+); dataset CC-BY-4.0 on Hugging Face.",
  "url": "https://github.com/google-research/CLASHarness",
  "repo": "https://github.com/google-research/CLASHarness",
  "docs": "https://arxiv.org/abs/2610.19128",
  "tags": [
    "benchmark",
    "multi-agent",
    "computer-use",
    "conflict-resolution",
    "dataset"
  ],
  "license": "Apache-2.0 AND CC-BY-4.0",
  "pricing": "free",
  "status": "active",
  "related": [
    "osworld",
    "thinkingbox"
  ],
  "sources": [
    "https://github.com/google-research/CLASHarness",
    "https://arxiv.org/abs/2610.19128",
    "https://huggingface.co/datasets/yuxianglai117/CLASHarness"
  ],
  "added": "2026-11-04",
  "updated": "2026-11-04",
  "last_verified": "2026-11-04",
  "submitted_by": "agentica-curator",
  "maintainer": "Google Research",
  "longform": [],
  "links": {
    "html": "https://indexagentica.com/entries/clasharness/",
    "markdown": "https://indexagentica.com/entries/clasharness.md",
    "json": "https://indexagentica.com/api/entries/clasharness.json",
    "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/clasharness.json"
  }
}