This startup wants to change how mathematicians do math

2026-03-25 · Source: MIT Technology Review · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Intermediate, medium

Summary

Axiom Math, a Palo Alto startup, has released Axplorer, a free AI tool designed to help mathematicians discover new patterns and solve long-standing problems. Axplorer is a redesigned, more efficient version of PatternBoost, co-developed by Axiom research scientist François Charton in 2024 at Meta. While PatternBoost required a supercomputer, Axplorer runs on a Mac Pro and achieved the same result for the Turán four-cycles problem in 2.5 hours, compared to PatternBoost's three weeks. The tool aims to democratize access to advanced AI for mathematical discovery, aligning with initiatives like DARPA's expMath. Unlike large language models (LLMs) that excel at derivative problems, Axplorer focuses on generating novel insights by iteratively refining patterns, similar to Google DeepMind's AlphaEvolve, but with greater accessibility.

Key takeaway

For AI scientists and mathematicians seeking to accelerate discovery, Axplorer offers a powerful, accessible tool for pattern generation. Unlike LLMs that often provide derivative solutions, Axplorer is designed for novel insights, potentially speeding up research on complex, unsolved problems. You should consider integrating Axplorer into your workflow, especially for exploratory math, to leverage its efficiency and open-source nature for generating new ideas and counterexamples.

Key insights

Axplorer offers an accessible AI tool for mathematicians to discover novel patterns and accelerate problem-solving.

Principles

• AI can generate new mathematical insights.
• Accessibility drives broader AI adoption.
• Efficiency is key for practical AI tools.

Method

Axplorer uses an iterative pattern generation process: users provide an example, the tool generates similar ones, users select interesting outputs, and the tool refines its generation based on feedback.

In practice

• Install Axplorer on a Mac Pro for pattern discovery.
• Use Axplorer to generate sample solutions or counterexamples.
• Explore graph theory problems with Axplorer's capabilities.

Topics

• Axiom Math
• Axplorer
• Mathematical Discovery
• Pattern Recognition
• Graph Theory

Code references

• AxiomMath/Axplorer

Best for: AI Scientist, AI Researcher, Research Scientist, AI Student

Related on AIssential

• An AI solution to an 80‑year‑old problem has shocked mathematicians — General-purpose AI models can autonomously solve long-standing mathematical conjectures by exploring vast solution spaces.
• She Raised $64M to Build an AI Math Prodigy | Carina Hong, CEO of Axiom — Axiom Math's AI combines formal verification with probabilistic generation to solve complex math problems and aims for broader application.
• Improving the academic workflow: Introducing two AI agents for better figures and peer review — AI agents can automate complex academic tasks like figure generation and peer review, improving efficiency and quality.
• How AI is changing the nature of mathematical research — AI tools are revolutionizing mathematical research by automating proof generation and contributing novel ideas, accelerating discovery.
• Advancing Mathematics Research with AI-Driven Formal Proof Search — LLM-driven formal proof search, verified by Lean, can solve open mathematical problems and advance research.
• Towards Generalist Agents for Accelerating Scientific Discovery171 — LLMs can accelerate scientific discovery by generating and refining hypotheses within agentic, iterative workflows.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by MIT Technology Review.