Axiom Formally Verifies the Stacks Project With AI Agents
Axiom says it has formally verified the Stacks Project, one of the largest collections of mathematical work, according to TechCrunch. Its AI agents translated roughly 7,654 pages into about 16 million lines of computer checked Lean code.
The Stacks Project is an open source mathematical reference started by Johan de Jong in 2005. It covers algebra, geometry and number theory. Formal verification converts proofs into code that a proof assistant checks line by line for logical consistency.
Axiom assigned its agents a loose hierarchy, allowing them to select tasks and work in parallel while preserving connections among definitions and theorems. The company also trained its own mathematics models and initially used a Lean specialist to guide the agents. The resulting library gives researchers a verified foundation for building further proofs in algebraic geometry.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Daily AI Brief.
Also, consider following us on social media:
Daily AI Brief
Daily report covering major AI developments and industry news, with both top stories and complete market updates
Humanoid Robot Makers
Companies building humanoid robots, from startups to Tesla and Boston Dynamics
Market report
2025 Generative AI in Professional Services Report
Thomson Reuters
This report by Thomson Reuters explores the integration and impact of generative AI technologies, such as ChatGPT and Microsoft Copilot, within the professional services sector. It highlights the growing adoption of GenAI tools across industries like legal, tax, accounting, and government, and discusses the challenges and opportunities these technologies present. The report also examines professionals' perceptions of GenAI and the need for strategic integration to maximize its value.
Read moreYou may also like
Axiomatic AI publishes its own test results for Lemma paper-checking AI
Anthropic Releases FlashProve to Verify AI Model Responses
&Truth Emerges From Stealth With $70 Million for Code Verification
OpenAI Releases 722 Math Manuscripts From Unreleased Model
OpenAI Math Release Omits Elements of Advisory Guidance
Daily AI Brief: the AI news that matters, in your inbox.