{
  "id": 4054,
  "url": "https://arxiv.org/abs/2605.19338v1",
  "title": "STAR-PólyaMath: Multi-Agent Reasoning under Persistent Meta-Strategic Supervision",
  "summary": "Frontier AI models and multi-agent systems have led to significant improvements in mathematical reasoning. However, for problems requiring extended, long-horizon reasoning, existing systems continue to suffer from fundamental reliability issues: hallucination accumulation, memory fragmentation, and imbalanced reasoning-tool trade-offs. In this paper, we introduce STAR-PólyaMath, a multi-agent framework that systematically addresses these challenges through meta-level supervision and structured R",
  "authors": "Jiaao Wu, Xian Zhang, Hanzhang Liu, Sophia Zhang, Fan Yang, Yinpeng Dong",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": "meta",
  "regions": null,
  "published_at": "2026-05-19T04:20:43.000Z",
  "fetched_at": "2026-07-14T16:30:41.584Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4054",
  "original_url": "https://arxiv.org/abs/2605.19338v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}