Saved in:
Bibliographic Details
Main Author: Ilin, Vasily
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.15929
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915903973621760
author Ilin, Vasily
author_facet Ilin, Vasily
contents We present a complete Lean 4 formalization of the equilibrium characterization in the Vlasov-Maxwell-Landau (VML) system, which describes the motion of charged plasma. The project demonstrates the full AI-assisted mathematical research loop: an AI reasoning model (Gemini DeepThink) generated the proof from a conjecture, an agentic coding tool (Claude Code) translated it into Lean from natural-language prompts, a specialized prover (Aristotle) closed 111 lemmas, and the Lean kernel verified the result. A single mathematician supervised the process over 10 days at a cost of \$200, writing zero lines of code. The entire development process is public: all 229 human prompts, and 213 git commits are archived in the repository. We report detailed lessons on AI failure modes -- hypothesis creep, definition-alignment bugs, agent avoidance behaviors -- and on what worked: the abstract/concrete proof split, adversarial self-review, and the critical role of human review of key definitions and theorem statements. Notably, the formalization was completed before the final draft of the corresponding math paper was finished.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15929
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Semi-Autonomous Formalization of the Vlasov-Maxwell-Landau Equilibrium
Ilin, Vasily
Artificial Intelligence
Analysis of PDEs
Logic
68V15 (primary), 68T01, 35Q83, 82D10 (secondary)
I.2.3; F.4.1; J.2
We present a complete Lean 4 formalization of the equilibrium characterization in the Vlasov-Maxwell-Landau (VML) system, which describes the motion of charged plasma. The project demonstrates the full AI-assisted mathematical research loop: an AI reasoning model (Gemini DeepThink) generated the proof from a conjecture, an agentic coding tool (Claude Code) translated it into Lean from natural-language prompts, a specialized prover (Aristotle) closed 111 lemmas, and the Lean kernel verified the result. A single mathematician supervised the process over 10 days at a cost of \$200, writing zero lines of code. The entire development process is public: all 229 human prompts, and 213 git commits are archived in the repository. We report detailed lessons on AI failure modes -- hypothesis creep, definition-alignment bugs, agent avoidance behaviors -- and on what worked: the abstract/concrete proof split, adversarial self-review, and the critical role of human review of key definitions and theorem statements. Notably, the formalization was completed before the final draft of the corresponding math paper was finished.
title Semi-Autonomous Formalization of the Vlasov-Maxwell-Landau Equilibrium
topic Artificial Intelligence
Analysis of PDEs
Logic
68V15 (primary), 68T01, 35Q83, 82D10 (secondary)
I.2.3; F.4.1; J.2
url https://arxiv.org/abs/2603.15929