📄 中文摘要
近期基础模型的进展使得推理系统能够在国际数学奥林匹克中达到金牌标准。然而，从竞赛级别的问题解决转向专业研究，需要在浩瀚的文献中导航并构建长时间跨度的证明。Aletheia 是一种数学研究代理，能够在自然语言中迭代生成、验证和修订解决方案。Aletheia 由先进版本的 Gemini Deep Think 驱动，专注于挑战性推理问题，采用了一种超越奥林匹克级别问题的新推理时间扩展法则，并通过密集的工具使用来应对数学研究的复杂性。
迈向自主数学研究
出处: Towards Autonomous Mathematics Research
发布: 2026年2月12日
📄 English Summary
Towards Autonomous Mathematics Research
Recent advancements in foundational models have led to reasoning systems capable of achieving gold-medal standards at the International Mathematical Olympiad. Transitioning from competition-level problem-solving to professional research involves navigating extensive literature and constructing long-horizon proofs. Aletheia, a math research agent, iteratively generates, verifies, and revises solutions in natural language. It is powered by an advanced version of Gemini Deep Think for challenging reasoning problems, a novel inference-time scaling law that extends beyond Olympiad-level problems, and intensive tool use to navigate the complexities of mathematical research.