arxivApril 7, 2026 at 4:00 AM1 min read

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

arXiv:2604.04898v1 Announce Type: cross Abstract: Proprietary AI systems have recently demonstrated impressive capabilities on complex proof-based problems, with gold-level performance reported at the 2025 International Mathematical Olympiad (IMO). However, the training pipelines behind these system

Read original article ↗

No replies yet. Be first.

arxiv7h ago

Advantage-Guided Diffusion for Model-Based Reinforcement Learning

arxiv7h ago

FluidFlow: a flow-matching generative model for fluid dynamics surrogates on unstructured meshes

arxiv7h ago

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

Related Articles

Advantage-Guided Diffusion for Model-Based Reinforcement Learning

FluidFlow: a flow-matching generative model for fluid dynamics surrogates on unstructured meshes

HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?