Base Date 2026-11-03
Last Run 2026-11-03 21:00:25
S&P 500
7,569
NDX 100
28,180
VIX
20.82
US 10Y
4.95%
DXY
101.86
WTI
$96.60
Gold
$3,932
USD/KRW
1,344
SOX
10,599
Trump Approve
35.4%
S&P 500
7,569
NDX 100
28,180
VIX
20.82
US 10Y
4.95%
DXY
101.86
WTI
$96.60
Gold
$3,932
USD/KRW
1,344
SOX
10,599
Trump Approve
35.4%
← AI Leaders: Moves & Papers
Paper summary · 2026-10-08 · Science

Automatically proving unsolved math problems with AI

Advancing mathematics research with AI-driven formal proof search
Pushmeet Kohli +20 more
Agents & coding AI for science
Read paper ↗ PDF ↗
What
We developed an AI agent that searches for mathematical proofs at scale by utilizing a language where a compiler verifies the proof steps.
Key result
This AI agent successfully and autonomously solved several unsolved math problems and conjectures.
Why it matters
It demonstrated the potential for AI to drive autonomous mathematical discoveries.

Background

While large language models excel at math tasks, their lack of reliability has limited their use in actual mathematical research. To address this, combining them with languages where programs can verify every proof step has been discussed.

Method

We built an agent that automatically finds mathematical proofs by alternating between AI and verification tools.

Main results

The agent autonomously solved 9 out of 353 unsolved Erdős problems and proved 44 out of 492 conjectures from the Online Encyclopedia of Integer Sequences. It is also being deployed and utilized in research on combinatorics, optimization, graph theory, algebraic geometry, and quantum optics.

Limitations & open points

The abstract does not provide detailed information on specific computational costs or the operating time of the agent.

Glossary

  • 대규모 언어 모델 — AI technology that can write and understand text like a human
  • 인공지능 에이전트 — An AI program that judges and acts on its own to achieve a goal

This summary was written by AI from the paper's abstract and reviewed by the editor. Summaries on this page were translated by AI from the editor-reviewed Korean version. Check the original for exact figures and context.

This page compiles published papers, official announcements and press reports for information only. Paper summaries are written by AI from the abstract and reviewed by the editor; they may differ from the original, so check the paper for anything important. Nothing here is a recommendation to buy or sell any security or investment advice. Career moves cite official announcements or major press reports; some career records come from Wikidata (CC0). Summaries on this page were translated by AI from the editor-reviewed Korean version.

🐩 Support Kobong's Treats
코봉이
If this page was helpful, feel free to support Kobong's treat fund too 🦴
💬 Community Comments
Anonymous nicknames based on IP · Abuse may result in restrictions
Loading...