Papers › Learning Formal Mathematics From Intrinsic Motivation

Learning Formal Mathematics From Intrinsic Motivation

30 Jun 2024arXiv:2407.00695archive 2025-07-28

Gabriel Poesia, David Broman, Nick Haber, Noah D. Goodman

How did humanity coax mathematics from the aether? We explore the Platonic view that mathematics can be discovered from its axioms - a game of conjecture and proof. We describe Minimo (Mathematics from Intrinsic Motivation): an agent that jointly learns to pose challenging problems for itself (conjecturing) and solve them (theorem proving). Given a mathematical domain axiomatized in dependent type theory, we first combine methods for constrained decoding and type-directed synthesis to sample valid conjectures from a language model. Our method guarantees well-formed conjectures by construction, even as we start with a randomly initialized model. We use the same model to represent a policy and value function for guiding proof search. Our agent targets generating hard but provable conjectures - a moving target, since its own theorem proving ability also improves as it trains. We propose novel methods for hindsight relabeling on proof search trees to significantly improve the agent's sample efficiency in both tasks. Experiments on 3 axiomatic domains (propositional logic, arithmetic and group theory) demonstrate that our agent can bootstrap from only the axioms, self-improving in generating true and challenging conjectures and in finding proofs.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2407.00695")

Code

Syntology Ran 6 of 12 code samples harvested from 2 repositories linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · our draft was wrong; 4 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 2 ran; community (archive-listed): 5 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

gpoesia/minimo officialmentioned on GitHubpytorch report
gpoesia/peano mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 6 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
1ran · our draft was wrong
4ran
6unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

get_task_result gpoesia/minimo/learning/bootstrap.py official repository ran · violated contract MIT (permissive) · 1b68e87818578318 · report
tqdm_if gpoesia/minimo/learning/proofsearch.py official repository ran · our draft was wrong MIT (permissive) · 75028df1d168888c · report
MonteCarloTreeSearch gpoesia/minimo/learning/proofsearch.py official repository unverified MIT (permissive) · 80047b94fe10028f · report
Policy gpoesia/minimo/learning/proofsearch.py official repository unverified MIT (permissive) · 125ede135fa4d524 · report
ProofStateNode gpoesia/minimo/learning/proofsearch.py official repository unverified MIT (permissive) · adb27c584b45f5df · report
TreeSearchNode gpoesia/minimo/learning/proofsearch.py official repository unverified MIT (permissive) · 65f79cc819d8f97e · report
value_color gpoesia/minimo/learning/proofsearch.py official repository unverified MIT (permissive) · 962c20c096635384 · report
compare_dependencies gpoesia/peano/learning/curriculum.py community (archive-listed) ran MIT (permissive) · 4e2a73751fad8636 · report
format gpoesia/peano/domains/generate.py community (archive-listed) ran fingerprinted MIT (permissive) · 572549ed9144b302 · report
sympy_to_sexp gpoesia/peano/domains/generate.py community (archive-listed) ran MIT (permissive) · 640bcf54dbb57530 · report
topologically_sort_dependencies gpoesia/peano/learning/curriculum.py community (archive-listed) ran MIT (permissive) · f15c4b4559c12a51 · report
generate_term gpoesia/peano/domains/generate.py community (archive-listed) unverified MIT (permissive) · 97211e408a9ced92 · report

Tasks

Automated Theorem ProvingLanguage ModelingLanguage Modelling

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections