LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization 事件

LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization arXiv:2606.05400v1 Announce Type: cross Abstract: Long-horizon autoformalization of research mathematics fails not only at hard lemmas, but at scale: statements drift, dependencies tangle, context decays, and local repairs corrupt distant work. We present LeanMarathon, a multi-agent harness for reliable research-level Lean autoformalization. Its core abstraction is an evolving blueprint: a Lean file t