An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics

arXiv:2605.13301v1 Announce Type: new Abstract: Recent progress in reasoning models has substantially advanced long-horizon mathematical and scientific problem solving, with

arXiv:2603.19828v1 Announce Type: new Abstract: Autoformalization aims to translate natural-language mathematics into compilable, machine-checkable statements. However, semantic

arXiv:2603.19220v1 Announce Type: cross Abstract: We introduce Nemotron-Cascade 2, an open 30B MoE model with 3B activated parameters that delivers best-in-class reasoning and

arXiv:2608.11941v2 Announce Type: new Abstract: We construct OEIS Open, a benchmark based on 492 open mathematical conjectures from the OEIS, formalized in Lean by Tsoukalas et

arXiv:2604.15839v1 Announce Type: new Abstract: Most ATP benchmarks embed the final answer within the formal statement -- a convention we call "Easy Mode" -- a design that