arXiv:2606.05400v1 Announce Type: new 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...
Läs hela artikeln hos källan.
Kommentarer (0)
Inga kommentarer ännu. Bli först med att kommentera!