{
  "id": 4106,
  "url": "https://arxiv.org/abs/2605.18580v2",
  "title": "When Outcome Looks Right But Discipline Fails: Trace-Based Evaluation Under Hidden Competitor State",
  "summary": "Outcome-only evaluation can certify economically unsafe agents: a policy can hit a business KPI while violating deployable behavioral discipline. In hotel pricing with hidden competitor state, a learner can achieve plausible revenue per available room while failing to preserve the rate discipline of a rule-based revenue-management competitor. We introduce discipline stability, a trace-based evaluation paradigm: define the benchmark behavior, restrict observations to the deployment regime, induce",
  "authors": "Peiying Zhu, Sidi Chang",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-18T15:58:34.000Z",
  "fetched_at": "2026-07-14T16:30:45.938Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4106",
  "original_url": "https://arxiv.org/abs/2605.18580v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}