English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

AI Verifies the 246 Bounded Prime Gaps Theorem: Axiom Math's AxiomProver Completes Full Lean 4 Formalization

Forum topic · QianXun · 2026-08-22

Summary

Axiom Math, a startup founded by a 25-year-old woman from Guangzhou, announced on August 17 that its multi-agent system AxiomProver completed a Lean 4 formal verification of the 246 bounded prime gaps theorem — the current frontier result in the twin primes chain, achieved through the Polymath8b collaboration led by James Maynard and Terence Tao after Yitang Zhang's 2013 breakthrough. Importantly, AxiomProver does not prove new theorems; it machine-verifies human proofs. Its pipeline uses four cooperating modules: an auto-formalizer that fills in the proof's skipped steps ('it is obvious that...') as Lean 4 code, a conjecturer that generates missing intermediate lemmas, a core engine that searches complete proof paths, and an auto-informalizer that translates the machine proof back into readable prose for mathematicians. Mathematician Ken Ono endorsed the result, with the paper publicly reviewable at primegaps.axiommath.ai/paper/. The milestone shifts Lean 4 formalization from an elite specialist skill toward a routine pipeline and gives the mathematical community concrete evidence in debates over AI-assisted proofs, echoing Terence Tao's proposal to delegate proof generation and verification to AI while mathematicians retain interpretation and publication judgment.

Axiom Math, a startup founded by a 25-year-old woman from Guangzhou, announced on August 17 that its multi-agent system AxiomProver completed a Lean 4 formalization and verification of the 246 bounded prime gaps theorem. The paper is publicly available at primegaps.axiommath.ai/paper/. On August 22, AI outlet 新智元 (New Intelligence) ran a feature on the milestone, pushing the mathematics community back into a discussion of "machine-verifiable" proofs that has been building for decades.

Why the number 246 matters

The twin primes conjecture asks whether there are infinitely many prime pairs differing by 2 — like 3 and 5, 11 and 13, 17 and 19. It remained unresolved through the 19th century. The chain of progress:

  • 2013: Yitang Zhang, then a 58-year-old lecturer at the University of New Hampshire, proved there are infinitely many prime pairs with gaps of at most 70 million.
  • James Maynard (Oxford) used a different method to push the bound down to 600, winning the 2022 Fields Medal partly for this work.
  • Maynard then joined forces with Fields medalist Terence Tao in the Polymath8b online collaboration, driving the bound to 246.
  • Nobody has moved the number a single step since. Ken Ono, Axiom Math's founding mathematician, calls the theorem "the ceiling of human understanding of primes."

    What AxiomProver actually does

    A crucial clarification: the system does not prove the theorem itself — it re-walks the already-proven human proof with machine verification. Four modules operate in a closed loop:

    1. Auto-formalizer — fills in every "obviously" and "it is easy to verify" skipped step as Lean 4 code. 2. Conjecturer — automatically generates missing intermediate lemmas. 3. Core engine — searches for complete proof paths. 4. Auto-informalizer — translates the machine proof back into natural language so mathematicians can review it.

    The system doesn't just stuff one theorem into Lean; the four modules relay to bridge the gaps, generate lemmas, connect proof paths, and read the result back — all four are indispensable.

    Why it matters

    This opens a very concrete path in how the math community absorbs AI. It follows Terence Tao's recent dialogue with Hong Wang, which raised the question philosophically: if AI produces too many proofs for mathematicians to read, what then? Tao's direction — "adoption": hand proof generation and verification to AI, and return professional exposition and publication to mathematicians. The AxiomProver pipeline makes the first half of that division of labor real, especially for a proof like the 246 theorem that is subtle, full of skipped steps, and impenetrable to direct AI reading.

    Deeper still is the methodological significance: an entire AI verification chain for a human-level theorem ran end-to-end through Lean 4. This is not a demo; a specific theorem is now locked in as an independently verifiable fact. In future debates over whether AI proofs can be published, the community has physical evidence on the table — a repeatable procedure (Lean 4 compiles, lemmas completed, informalization reviewed) rather than a subjective "I spent a few days digesting it."

    It was also genuinely hard: the human 246 proof relies on many leaps like "obviously" or "this completes the proof." AxiomProver had to break each into formalizable subgoals, generate lemmas, and connect them — a break anywhere voids the whole verification. That is why automated Lean 4 formalization is considered "the hard bone of math AI": it can't be solved by bigger models alone, but must be chewed through piece by piece, as engineering. Ken Ono's endorsement reflects the fact that, once this pipeline works, Lean 4 formalization begins sliding from "an extreme sport for individual geniuses" toward "a routine pipeline task."

    What to watch next

  • Formalizing more of the twin primes ladder. If Axiom Math next formalizes other milestones — Maynard's 2014 sieve results, or Goldston–Pintz–Yıldırım's 2005 small-gap work — the entire progression ladder toward the twin primes conjecture would be pinned down by machines.
  • An accelerating data–engine–feedback flywheel for automated formalization. On August 19, OpenAI's Astra wrote proof certificates for 10 open theorems in Lean 4 directly into a paper; AxiomProver turns "back-filling formalizations of published theorems" into a pipeline. When these two routes converge, tolerance for AI-assisted papers in the math community should rise quickly.
  • "What do mathematicians still do?" Tao asked at a recent ICM lecture: if answers can be mass-produced by AI, what should mathematical research pursue? Verification-only tools like AxiomProver hint at the answer: the scarcest skill won't be problem-solving, but judgment — choosing which problems deserve formalization and how to route formalized results back into mainstream journals.
In short: this isn't the story of "AI proved another problem." It's the story of "AI ran a complete Lean 4 verification of humanity's hardest prime theorem." From today, "Lean 4 passes / fails" may serve as a colder, more objective acceptance criterion than journal peer review.

Tags

#lean-4#formal-verification#twin-primes-conjecture#ai-mathematics#axiom-math#terence-tao#polymath8b#automated-proving

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178633837