{
  "id": 15858,
  "url": "https://arxiv.org/abs/2608.02358",
  "title": "ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step",
  "summary": "To operate robustly in open-world environments, autonomous agents should be able to infer the behavior of unfamiliar systems through interaction alone, even in the absence of documentation. However, existing tool-use benchmarks expose semantic tool schemas in static environments, allowing agents to rely on prior knowledge rather than autonomous discovery. To address this limitation, we introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning. By rem",
  "authors": "Vernon Toh, Navonil Majumder, Zhengyuan Liu, Nancy F. Chen, Soujanya Poria",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-02T20:00:00.000Z",
  "fetched_at": "2026-08-04T05:10:21.797Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/15858",
  "original_url": "https://arxiv.org/abs/2608.02358",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}