Compile-Gated Lean Proof Refactoring with Enterprise Agent Practices: A Model per Step under a US$3 Cap, Followed by Programmatic Rewrite Rules
cs.SE, cs.AI, cs.LO
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/bobbercheng/lean-refactor-closed
Terminology
Sources
- ProofOptimizer: Training Language Models to Simplify Proofs without Human Demonstrations
- Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search
- PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters