{
  "id": 5910,
  "url": "https://arxiv.org/abs/2604.12116v2",
  "title": "The A-R Behavioral Space: Execution-Level Profiling of Tool-Using Language Model Agents in Organizational Deployment",
  "summary": "Large language models (LLMs) are increasingly deployed as tool-augmented agents capable of executing system-level operations. While existing benchmarks primarily assess textual alignment or task success, less attention has been paid to the structural relationship between linguistic signaling and executable behavior under varying autonomy scaffolds. This study introduces an execution-layer be-havioral measurement approach based on a two-dimensional A-R space defined by Action Rate (A) and Refusal",
  "authors": "Shasha Yu, Fiona Carroll, Barry L. Bentley",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-13T22:50:21.000Z",
  "fetched_at": "2026-07-14T16:32:06.468Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5910",
  "original_url": "https://arxiv.org/abs/2604.12116v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}