We introduce the Kimina Lean Server, an open-source project designed as a high-performance verifier for reinforcement learning pipelines. Built on top of the Lean REPL (Read-Eval-Print Loop) maintained by the Lean FRO, our server combines server-side parallelism by managing multiple Lean processes in parallel with a Least Recently Used (LRU) caching mechanism that reuses Lean imports across requests. On the client side, a lightweight Python package enables submitting proof batches and receiving Lean feedback, including extracted tactics and tactic states. Together, these features enable a scalable workflow for large-scale verification and data extraction. In our experiments, the Kimina Lean Server outperforms previous Lean interaction tools, achieving a 1.5 to 2 times speedup in verification time. Moreover, its improved efficiency has enabled its use in the large-scale training of state-of-the-art models such as Kimina-Prover. We hope that our open-source project will support the neural theorem proving community and accelerate future progress by enabling efficient large-scale verification and proof data extraction.
@article{arxiv.2504.21230,
title = {Kimina Lean Server: A High-Performance Lean Server for Large-Scale Verification},
author = {Marco Dos Santos and Hugues de Saxcé and Haiming Wang and Ran Wang and Mantas Baksys and Mert Unsal and Junqi Liu and Zhengying Liu and Jia Li},
journal= {arXiv preprint arXiv:2504.21230},
year = {2025}
}
Comments
Accepted to the 5th MATH-AI Workshop at NeurIPS 2025