{"ID":2831259,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.08743","arxiv_id":"2512.08743","title":"Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligence","abstract":"Foundation models (FMs) are increasingly assuming the role of the ''brain'' of AI agents. While recent efforts have begun to equip FMs with native single-agent abilities -- such as GUI interaction or integrated tool use -- we argue that the next frontier is endowing FMs with native multi-agent intelligence. We identify four core capabilities of FMs in multi-agent contexts: understanding, planning, efficient communication, and adaptation. Contrary to assumptions about the spontaneous emergence of such abilities, we provide extensive empirical evidence, across 41 large language models and 7 challenging benchmarks, showing that scaling single-agent performance alone does not automatically yield robust multi-agent intelligence. To address this gap, we outline key research directions -- spanning dataset construction, evaluation, training paradigms, and safety considerations -- for building FMs with native multi-agent intelligence.","short_abstract":"Foundation models (FMs) are increasingly assuming the role of the ''brain'' of AI agents. While recent efforts have begun to equip FMs with native single-agent abilities -- such as GUI interaction or integrated tool use -- we argue that the next frontier is endowing FMs with native multi-agent intelligence. We identify...","url_abs":"https://arxiv.org/abs/2512.08743","url_pdf":"https://arxiv.org/pdf/2512.08743v3","authors":"[\"Shuyue Hu\",\"Haoyang Yan\",\"Yiqun Zhang\",\"Yang Chen\",\"Dongzhan Zhou\",\"Lei Bai\"]","published":"2025-12-09T15:51:36Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.MA\"]","methods":"[\"Language Model\"]","has_code":false}