{
  "id": 4813,
  "url": "https://arxiv.org/abs/2605.06529v1",
  "title": "Market-Alignment Risk in Pricing Agents: Trace Diagnostics and Trace-Prior RL under Hidden Competitor State",
  "summary": "Outcome metrics can certify the wrong behavior. We study this failure in a two-hotel revenue-management simulator where Hotel A trains an agent against a fixed rule-based revenue-management competitor, Hotel B. A standard learning agent can obtain near-reference revenue per available room (RevPAR) while failing to learn market-like yield management: it sells too aggressively, undercuts, or collapses to modal price buckets. We diagnose this as a Goodhart-style failure under partial observability.",
  "authors": "Peiying Zhu, Sidi Chang",
  "category": "research",
  "topics": "safety-alignment,healthcare,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-07T16:31:39.000Z",
  "fetched_at": "2026-07-14T16:31:17.581Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4813",
  "original_url": "https://arxiv.org/abs/2605.06529v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}