AIToday
Qiita 機械学習Published: Nov 17, 2026, 04:00 JST

Lean overtakes Isabelle as theorem-proving research shifts, survey of 208 papers shows

Send on LINE
Lean overtakes Isabelle as theorem-proving research shifts, survey of 208 papers shows

3 Key Points

  1. What happened

    A survey count of 208 deep-learning theorem-proving papers found only 46 target Lean, versus 24 for Isabelle, 18 for Mizar and 17 for Coq. Lean research went from zero in 2021 to 6 in 2022 and 17 in 2023, exceeding all other systems combined that year.

  2. Why it matters

    The countries that built the foundational tools do not dominate current research.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Context & Analysis

The count draws on the DL4TP bibliography attached to a COLM 2024 survey, which labels each paper by the proof assistant it targets. Because a single paper can target several systems, it is counted once per system, and the list is not exhaustive.

The body also traces where the early work came from. A small group of researchers around Cambridge and Edinburgh produced LISA in 2021, then Thor and Draft, Sketch, and Prove in 2022, and Magnushammer and Llemma in 2023. A separate lineage starts from OpenAI's GPT-f in 2020 and runs through miniF2F and LISA. These threads suggest the field's direction was shaped by a handful of people before it spread to large corporate labs.

The country sections complicate any simple national scoreboard. Japan has no identified national project naming theorem proving, yet a Kyoto University-led effort produced Prover Agent, an 8B-parameter model that scored 88.1% on miniF2F. China's State Council issued a 2025 AI action document, but it does not name theorem proving; corporate labs such as DeepSeek and universities moved on their own. The U.S. and U.K. also show no named national project, though U.K. work built heavily on Isabelle, a tool co-maintained with Germany.

FAQ
Which proof assistant has the most deep-learning research?
Lean, with 46 of the 208 duplicate-removed papers, ahead of Isabelle at 24 and Mizar at 18.
Where did the paper list come from?
It is the DL4TP list accompanying a COLM 2024 survey on deep learning for theorem proving. The list was last updated in May 2025, so 2025 figures are partial and 2026 is not included.
Did the count include which country each author is from?
No. Author affiliations are not recorded in the paper list, so national affiliations could not be counted and were not estimated from names.
Qiita 機械学習Read Original Article
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Next articleFSTab maps AI coding habits to hidden flaws, hitting 85.67% match