AI RESEARCH

FATE: A Formal Benchmark Series for Frontier Algebra of Multiple Difficulty Levels

arXiv CS.LG

ArXi:2511.02872v4 Announce Type: replace Recent advances in large language models (LLMs) have nstrated impressive capabilities in formal theorem proving, particularly on contest-based mathematical benchmarks like the IMO. However, these contests do not reflect the depth, breadth, and abstraction of modern mathematical research. To bridge this gap, we