Models

1000 个 Fable 5.2 智能体 30 小时完成费马大定理形式化

Why we picked it

Anthropic 用 1000 个 Fable 5.2 智能体把费马大定理证明完整形式化,30 小时跑完,同设置下 Opus 5.5 只做到 26%。做形式化验证或数学相关工作的人应该看看多智能体拆任务的具体玩法。

Anthropic 宣布,1000 个 Fable 5.2 智能体组成的团队在 30 小时内完成了费马大定理证明的完整形式化,把证明逐步翻译成计算机可验证的语言。

Body

在完全相同的实验设置下,Opus 5.5 用 18 小时只完成了 26%,到 30 小时也几乎没有新增进度。这说明两者在长程协作、任务拆分与形式化推理能力上的差距是数量级级别的,而非微调差异。

费马大定理的形式化一直是检验数学 AI 系统的标志性难题,此前相关工作通常需要数学家团队数月投入。多智能体规模扩展加长时程任务调度若能复现,将直接改变形式化验证(如 Lean 生态)和复杂数学工程的工作方式。

Original · Claude

A team of 1,000 Fable 5.2 agents fully formalized Fermat’s Last Theorem in 30 hours, translating the proof into a language a computer can check step by step. With the same setup, Opus 5.5 completed only 26% in 18 hours, and barely made any more progress after 30 hours.📊 419 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Fable 5.2, Opus 5.5, Anthropic, 智能体.

Source attribution: curated from Claude (@claudeai).