MerLean: An Agentic Framework for Autoformalization in Quantum Computation
This provides a practical tool for machine-verified peer review in quantum computation and related fields, though it is incremental as it builds on existing autoformalization concepts.
The authors tackled the problem of autoformalization in quantum computation by developing MerLean, an agentic framework that automatically extracts mathematical statements from LaTeX, formalizes them into verified Lean 4 code, and translates them back to human-readable LaTeX. They evaluated it on three quantum computing papers, producing 2,050 Lean declarations from 114 statements with end-to-end formalization on all papers, reducing verification burden to only new definitions and axioms.
We introduce MerLean, a fully automated agentic framework for autoformalization in quantum computation. MerLean extracts mathematical statements from \LaTeX{} source files, formalizes them into verified Lean~4 code built on Mathlib, and translates the result back into human-readable \LaTeX{} for semantic review. We evaluate MerLean on three theoretical quantum computing papers producing 2,050 Lean declarations from 114 statements in total. MerLean achieves end-to-end formalization on all three papers, reducing the verification burden to only the newly introduced definitions and axioms. Our results demonstrate that agentic autoformalization can scale to frontier research, offering both a practical tool for machine-verified peer review and a scalable engine for mining high-quality synthetic data to train future reasoning models. Our approach can also be generalized to any other rigorous research in mathematics and theoretical physics.