{
  "id": 96,
  "url": "https://arxiv.org/abs/2607.08252v1",
  "title": "AutoPersonas: A Multi-Timescale Loop Engine for Open-Ended Persona Evolution",
  "summary": "Long-term persona agents must remain identifiable while adapting to new events, relationships, evidence, and social conditions. We identify self-locking as a runtime failure mode in continuing persona-life loops: locally plausible events keep appearing while the generated life collapses toward familiar environments, weak relationships, suspended decisions, and stale life stages. We trace this failure to model-level convergence toward high-probability behavioral channels and system-level context ",
  "authors": "Mengchen Li",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-09T08:56:30.000Z",
  "fetched_at": "2026-07-14T14:14:15.667Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/96",
  "original_url": "https://arxiv.org/abs/2607.08252v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}