发表机构
Google Research（谷歌研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Cogentic是一个多智能体框架，通过迭代证明-验证循环和持久账本，在开放数学问题上自动发现证明，已在五个开放问题上取得新颖结果。
AI 中文摘要
我们提出了Cogentic，一个用于在开放研究问题上自动发现证明的多智能体框架。虽然前沿语言模型能够一次性生成强大的数学想法，但对于需要探索多个相互竞争的猜想、克服微妙的技术障碍以及在长时间跨度内保留中间进展的开放问题，单次生成往往是不够的。Cogentic通过一个迭代的证明-验证循环来解决这些挑战，在该循环中，一个编排器将一组独立的证明者分配到不同的证明方向上，将其输出提交给几个专门组件的对抗性验证，并将确认的中间结果提升到一个持久的已验证账本中，后续轮次在此基础上构建。该框架旨在能够解决研究级别的数学和理论计算机科学问题。使用Gemini作为基础模型，Cogentic在在线学习、拍卖理论和机制设计领域的五个开放问题上产生了新颖的结果。每个结果都经过领域专家的独立验证，并在配套论文中完整展开。我们在以下网址列出这些结果以及验证后的新结果：此https URL。
英文摘要
We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong mathematical ideas in a single shot, single-shot generation is often insufficient for open problems that require exploring multiple competing conjectures, overcoming subtle technical obstructions, and retaining intermediate progress over a long horizon. Cogentic addresses these challenges through an iterative prove-verify loop in which an orchestrator allocates a population of independent provers across distinct proof directions, subjects their output to adversarial verification by several specialized components, and promotes confirmed intermediate results into a persistent verified ledger that later rounds build on. The harness is designed to be able to solve research-level math and theoretical computer science problems. Using either Gemini 3.1 Pro or an early version of Gemini 4 Argon as the base model, Cogentic produced novel results on open problems across online learning, auction theory, and mechanism design. Each result was independently verified by domain experts and is developed in full in companion papers. We list these results, and new ones as they are verified, at https://sites.google.com/view/cogentic .
