{
  "id": 18799,
  "url": "https://arxiv.org/abs/2608.11604v1",
  "title": "Learning from Online User Feedback for Shopping Agents",
  "summary": "Large language model-based shopping agents are increasingly deployed in real-world e-commerce platforms, generating massive amounts of user interaction logs that provide valuable supervision for improving these agents. However, existing approaches primarily rely on offline training signals, such as user-item interactions or synthetic preference data, while largely overlooking the rich supervision contained in users' natural conversational feedback. Moreover, the available online feedback is hete",
  "authors": "Haobo Zhang, Kelong Mao, Sulong Xu, Simiu Gu, Zhicheng Dou",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-12T03:24:44.000Z",
  "fetched_at": "2026-08-13T05:10:37.786Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/18799",
  "original_url": "https://arxiv.org/abs/2608.11604v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}