cs.SENov 9, 2026

Compile-Gated Lean Proof Refactoring with Enterprise Agent Practices: A Model per Step under a US$3 Cap, Followed by Programmatic Rewrite Rules

Authors: Bobber Cheng

Organizations: Vexorium

Abstract

Our closed-track entry (Arena username Vexorium-Agent) scored 86.31 points on the final board (L = 77.07, H = 81.86, Z = 100) over the 60 final problems, against 33.33 for the reference proofs, 8th at the deadline (top: 92.57), for US$166.33 at list prices with every call counted (per problem: mean US$2.772, at most US$2.874; US$3 cap). Three practices carry the entry. First, each paid stage runs the model that measured best per dollar for it among the 9 we tested in our own harness: GPT-6.1 Sol the early sessions, GPT-6.1 Terra the later ones and the tail at 70% of Sol's cost per turn, and Gemini 4 Argon the review and repair; Sol also runs the style rewrite. Second, what our development and research runs learned ships as compiler-checked programmatic rewrite rules rather than prompt text (+0.93 points from rules fixed before the release; +0.26 and +0.30, in sample, from passes built or switched on after the release). Third, every call is recorded and reviewed before each change (all 9 board scores came within -0.063 to +0.015 points of our meter's prediction). The harness, gate and many of these rules also serve our open-track entry. We report the full bill and the spread of three runs.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search

    May 18, 2026Jialin Lu, Soonho Kong, Rodrigo Stehling +4Large Language Model-Guided OptimizationLean Theorem Proving

  2. Do Theorem Provers Need Theorem-Proving Agents? mini-Lean-agent: A Coding-Agent Baseline for Lean

    Oct 12, 2026Tomas Ortega, Simon Park, Ayush Khaitan +3Large Language Model-Guided Theorem ProvingAutomated Theorem Proving

  3. Optimizing the Cost-Quality Tradeoff of Agentic Theorem Provers in Lean

    Jun 3, 2026Kári Rögnvaldsson, Chenhao Sun, Jasper Dekoninck +1Automated Theorem ProvingLean Theorem Proving