{
  "id": 4358,
  "url": "https://arxiv.org/abs/2605.14205v2",
  "title": "SimPersona: Learning Discrete Buyer Personas from Raw Clickstreams for Grounded E-Commerce Agents",
  "summary": "LLM-based web agents can navigate live storefronts, yet they often collapse to a single \"average buyer\" policy, failing to capture the heterogeneous and distributional nature of real buyer populations. Existing personalization methods rely on hand-crafted prompt-based personas that are brittle, difficult to scale, context-inefficient, and unable to faithfully represent population-level behavior. We introduce SimPersona, a novel framework that learns discrete buyer types from historical traffic a",
  "authors": "Zahra Zanjani Foumani, Alberto Castelo, Shuang Xie, Ted Chaiwachirasak, Han Li, Lingyun Wang",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-14T00:01:11.000Z",
  "fetched_at": "2026-07-14T16:30:54.923Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4358",
  "original_url": "https://arxiv.org/abs/2605.14205v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}