微软研究院称借助人类引导的AI智能体证明KLS猜想
AI 总结
微软研究院称,包括其机器学习与优化团队张新智(Xinzhi Zhang)在内的两位研究者证明了Kannan–Lovász–Simonovits(KLS)猜想。这一1995年提出的高维几何与概率问题追问:对一大类高维概率分布,最优的平坦(超平面)切割是否与任意形状的最优切割效果相当,且差距不超过一个与维数无关的通用常数。博客称该证明给出了不依赖维数的界,优于2026年7月一项界仍随维数缓慢增长的结果;最后一步是把递归改进整体重复一遍,使各阶段误差累积后仍被通用常数控制。文章称研究源于人类主导的智能体流程:AI系统探索了100多条候选路径,研究者负责评估、剪枝并调整方向;同日另一组专家也发布了完整的并行证明,Lean中的机器可检验形式化验证计划在最终审阅后发布。
深度见解
据该博客,解决KLS移除了理解科学与计算中随机算法效率的一大理论障碍,许多此前以该猜想为前提的结果如今可以无条件陈述。
Microsoft researcher and collaborator combine new mathematical ideas with human-directed AI to resolve a central problem in high-dimensional geometry and probability

At a glance
- Fundamental scientific breakthrough: Researchers resolved the Kannan-Lovász-Simonovits (KLS) conjecture, a 31-year-old problem widely regarded as one of the central open questions in high-dimensional geometry, with implications for statistics, optimization, algorithms, and computer science.
- A universal geometric principle: The result establishes a universal geometric principle for log-concave distributions, showing that simple flat cuts can capture their narrowest bottlenecks within a fixed factor, regardless of dimension.
- Human-AI collaboration: The breakthrough emerged from a human-directed agentic research process in which AI systems explored mathematical possibilities while researchers evaluated, pruned, and redirected the search.
- Independent confirmation: Multiple independent researchers have validated this research, identifying its central criterion as the key breakthrough, followed by a machine-checked formal verification.