Prove2Me crowd-sources Lean missions; six agents write 151K lines on consumer plans

Prove2Me: An Open Collaborative Platform for Scaling Math Formalization

Shuze Chen, Kunal Marwaha, Xiaoyang Lu, Henry Yuen, Tianyi Peng

cs.AI, cs.LO, cs.MA

2026-08-28

Prove2Me splits theorems from proofs and decomposes goals via proof-sketches. Bandit Algorithms yielded 151K Lean lines with 6 agents on ~$400 plans in 13 days.

What problem this solves

Lean 4 can machine-check theorems. Large formalization projects still stall on people. Scholze's Liquid Tensor Experiment took about 18 months of community work. Kevin Buzzard's Fermat's Last Theorem effort is funded for five years; he has said he cannot finish it alone. AI agents now dump textbooks and papers into Lean at speed, but three bottlenecks remain. Faithfulness of a statement to the intended claim still needs a human. GitHub dumps of tightly coupled theorems are hard to reuse one lemma at a time. The impressive swarms run on one lab's internal compute.

Prove2Me tries to make formalization a crowd-sourced mission: humans audit a small core of statements, agents fill in proofs, and proofs can import one another.

Method

The platform splits theorems and proofs into two immutable objects. A theorem card holds a natural-language description, a preamble, and a Lean statement ending in sorry. A proof must declare theorem solution with exactly that type and no sorry or new axioms. The backend checks the Curry-Howard match. Agents can also submit a negation as a disproof.

Human audit is confined to a mission's core: the goal theorem, its definitions, and milestone lemmas. The captain need not write Lean, but must click every core statement. An independent auditor agent does a read-back: it sees only the Lean declaration, not the source, and renders it as LaTeX so a human compares two math statements. Bourigault et al. report that a Lean-as-judge audit found only about 43% of proved statements faithful, which is why this human gate stays.

Collaboration runs through proof-sketches. A sorry-free proof may import other platform theorems, including still-open ones. Once a parent sketch is accepted, each child lemma becomes its own problem; when the children close, the parent auto-resolves. Immutability is what makes local correctness compose. Milestones pin canonical formalizations of key source lemmas so parallel agents do not fork incompatible restatements. Closed atomic theorems enter Formalpedia, searchable by the natural-language descriptions agents must file, and later sketches can import them. Credit accrues both for closing open theorems and for proposing statements that later proofs import.

Results

Case studies from mid-June to late July 2026, which the paper flags as not a controlled experiment:

MissionTypeLean LOCCost conventionAgentsDays
Gloeckle et al. algebraic combinatorics (external)Textbook130K$100k API30,000 runs7
Exact Matrix CompletionPaper81K$600 subscriptions916
Sipser–Gács–LautemannPaper55K$400 subscriptions38
Bandit AlgorithmsTextbook151K$400 subscriptions613
Introduction to Linear OptimizationTextbook17K$200 subscriptions47

The largest Prove2Me mission matches the centralized swarm in size (151K vs 130K lines) with 6 agents on two consumer plans. The Sensitivity Conjecture mission closed all four milestones. API invoices and flat-rate subscriptions are not comparable.

Why it matters

The skill bar for contributing Lean drops from "knows the proof assistant" to "can steer an agent in natural language." For someone who wants a paper or textbook formalized, a mission keeps the audit surface on the core statements and lets agents invent intermediate lemmas. Formalpedia makes those lemmas independently importable, which a monolithic Git repo does not.

This is mechanism design, not a new prover. The platform does not claim to out-prove AlphaProof.

Limitations

The case studies mix corpora, difficulty, working patterns, and model generations. They cannot separate a stronger model from the harness. Subscription cost is estimated as about $200 per month times the number of human contributors, which does not line up with Gloeckle et al.'s metered API bill.

Humans still audit the mission core. Statement faithfulness has no scalable automatic guarantee. Open submission invites junk and adversarial content; a reputation system is still a wish. How decentralized, asynchronous agents should share context is left open. Choosing what is worth formalizing, and how to cut milestones, remains human judgment.

Terms

Source

What people are saying

Related papers

All paper explainers