{
  "id": 5906,
  "url": "https://arxiv.org/abs/2604.12147v2",
  "title": "Evaluating Plan Compliance in Autonomous Programming Agents",
  "summary": "Agents aspire to eliminate the need for task-specific prompt crafting through autonomous reason-act-observe loops. Still, they are commonly instructed to follow a task-specific plan for guidance, e.g., to resolve software issues following phases for navigation, reproduction, patch, and validation. Unfortunately, it is unknown to what extent agents actually follow such instructed plans. Without such an analysis, determining the extent agents comply with a given plan, it is impossible to assess wh",
  "authors": "Shuyang Liu, Saman Dehghan, Jatin Ganhotra, Martin Hirzel, Reyhaneh Jabbarvand",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-13T23:54:55.000Z",
  "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/5906",
  "original_url": "https://arxiv.org/abs/2604.12147v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}