Diffusion-Proof: Formal Theorem Proving via Diffusion Language Models
Diffusion-Proof is the first application of diffusion language models to formal mathematics, pairing dLLM-Prover-7B (full proof generation) with dLLM-Corrector-7B (bidirectional proof correction via in-filling). The system achieves +1.61% on ProofNet-Test and +6.14% on MiniF2F-Test over baselines and solves an IMO problem that DeepSeek-Prover-V2-7B could not.
Why it matters
Demonstrates that diffusion LLMs can outperform autoregressive models on formal theorem proving, where compounding token-level errors are especially costly.
Importance: 2/5
Solid research paper opening a new direction for diffusion models in formal mathematics.