{
  "id": 1551,
  "url": "https://arxiv.org/abs/2607.08768",
  "title": "UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks",
  "summary": "The rapid development of large language models and multimodal large language models has accelerated the emergence of proactive agents capable of operating everyday tools and assisting users in real-world environments. However, existing benchmarks struggle to evaluate such agents effectively, as they often rely on sandboxed environments and single-turn evaluation paradigms. Moreover, their scenario-based task taxonomies mix multiple model capabilities within the same task category, making it diff",
  "authors": "Zhekai Chen, Chengqi Duan, Kaiyue Sun, Bohao Li, Yuqing Wang, Manyuan Zhang",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-08T20:00:00.000Z",
  "fetched_at": "2026-07-14T16:04:12.223Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/1551",
  "original_url": "https://arxiv.org/abs/2607.08768",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}