RESEARCH

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

ArXiv cs.AI · Sat, 06 Jun 2026 04:00:00 GMT

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-agen

Read original source Discuss with A.S.I.S