{
  "id": 16931,
  "url": "https://arxiv.org/abs/2608.04872v1",
  "title": "A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination",
  "summary": "Symbolic regression aims to discover closed-form equations from data, but existing LLM-guided methods often rely on a unified proposal loop that compresses heterogeneous search failures into a scalar score and a single prompt. We propose A-SR, a self-evolving agentic framework that shifts the control unit from expression edits to role-conditioned evidence views. A-SR coordinates formula discovery through routing among coordination protocols, an online evaluator-reward role policy, and state-rout",
  "authors": "Wenxiao Zhao, Dong Liu, Kaiyi Xu, Feng Liu, Zhen Zhao, Fei Ben, Shu Wang, Wenhao Li, Yingnian Wu, Fenghua Ling, Haobo Li, Lei Bai",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-05T14:01:10.000Z",
  "fetched_at": "2026-08-06T05:10:11.148Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/16931",
  "original_url": "https://arxiv.org/abs/2608.04872v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}