微软研究员借助 AI 智能体探索百余条路径，证明 31 年前的 KLS 猜想
A math problem older than Google has been solved, with AI doing much of the searching.
微软研究员借助 AI 智能体探索约 100 条研究路径，完成了对 1995 年提出、已有 31 年历史的 Kannan-Lovász-Simonovits（KLS）猜想的证明，成稿约 140 页。AI 负责探索候选方法、执行推导、协助撰写手稿并做内部证明检查，而完成证明的递归方法和误差界归功于两位研究者。该猜想可理解为：随机游走在凸形状内部不会被狭窄通道困住，即使在高维空间也能高效探索整个形状。
正文
当前显示原文，中文全文译文尚未就绪。
A math problem older than Google has been solved, with AI doing much of the searching.
Microsoft researcher proved this 31-year-old Math conjecture (Kannan-Lovász-Simonovits conjecture) after AI agents explored over 100 approaches.
A 140-page proof, more than 100 AI-explored paths now have closed a question mathematicians had been working on since 1995.
A human-directed search, with AI agents exploring roughly 100 research trajectories while a researcher cut weak directions between rounds, produced the criterion underpinning Song and Zhang’s proof of the Kannan-Lovász-Simonovits (KLS) conjecture.
The AI explored candidate approaches, carried out derivations, helped prepare the manuscript and ran internal proof checks, while the recursive method and the error bound that finished the proof are credited to the 2 researchers.
About the Kannan-Lovász-Simonovits conjecture: Picture a random walker wandering inside a convex shape: the conjecture says no secret narrow passage can trap it, so it can explore the whole shape efficiently, even in huge dimensions.