Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation
Quick Answer
Pythagoras-Prover introduces a compute-efficient family of Lean theorem provers, outperforming DeepSeek-Prover-V2-671B with 167x fewer parameters and achieving 93.0% on MiniF2F-Test.
Quick Take
The 4B model surpasses previous benchmarks, demonstrating effective training strategies and augmented formalization techniques.
Key Points
- Pythagoras-Prover includes autoregressive models with 4B and 32B parameters.
- The 32B model sets the open-source state of the art at 93.0% on MiniF2F-Test.
- Pythagoras-Prover-4B achieves 86.1% on MiniF2F-Test with significantly fewer parameters.
- Augmented Lean Formalisation (ALF) enhances training data without formal verification.
- Dynamic proof-reasoning filtering maintains informative proof traces within an 8k-token context.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Modern Lean theorem provers achieve strong performance only with substantial training and inference compute, driven in part by scarce verified proof data and the long reasoning traces of formal proof search, making both supervised fine-tuning (SFT) and sampling expensive. We introduce Pythagoras-Prover, a compute-efficient open-source family of Lean theorem provers built for practical compute budgets. The family spans two generation paradigms: autoregressive models at 4B and 32B parameters, and a first proof-of-concept diffusion-based prover (4B) that iteratively refines Lean proofs at inference time. For training efficiency, we build a Lean-verified corpus stratified into easy, medium, and hard problems for curriculum SFT, so models acquire proof skills progressively from shorter, simpler proofs to longer, harder ones. During SFT, a dynamic proof-reasoning filtering scheme preserves informative proof traces while keeping each instance within an 8k-token context budget. We also introduce Augmented Lean Formalisation (ALF), which expands scarce verified corpora into variants of formal statements, populated via self-distillation for extra training signal without formally verifying every mutated instance. By perturbing known problems while preserving their formal character, ALF reduces reliance on any statement's surface form. Empirically, Pythagoras-Prover-4B surpasses DeepSeek-Prover-V2-671B at pass@32 on MiniF2F-Test (86.1% vs 82.4%) with ~167x fewer parameters, while Pythagoras-Prover-32B sets the open-source state of the art at 93.0% on MiniF2F-Test and solves 93 of 672 PutnamBench problems. We release MiniF2F-ALF, an ALF-mutated contamination-sensitive benchmark on which every evaluated model loses accuracy; here our 32B remains strongest and our 4B matches the prior state of the art, Goedel-Prover-V2-32B.
| Comments: | Pythagoras-Prover: Technical Report |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.12594 [cs.AI] |
| (or arXiv:2606.12594v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.12594 arXiv-issued DOI via DataCite |
Submission history
From: Joshua Jun Leang Ong [view email]
[v1]
Wed, 10 Jun 2026 18:43:11 UTC (1,138 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.