CoqPilot, a plugin for LLM-based generation of proofs

TL;DR

CoqPilot is a VS Code plugin that automates Coq proof writing by integrating LLMs and other methods to generate and verify proof candidates for proof holes, facilitating experiments and benchmarking in proof generation.

Contribution

It introduces a seamless, zero-setup platform for combining multiple proof generation approaches and conducting LLM-based experiments on Coq proof generation.

Findings

Developed a benchmarking system for Coq proof generation methods.

Demonstrated the framework's capabilities through an experiment.

Enabled automated proof hole filling with LLMs and verification.

Abstract

We present CoqPilot, a VS Code extension designed to help automate writing of Coq proofs. The plugin collects the parts of proofs marked with the admit tactic in a Coq file, i.e., proof holes, and combines LLMs along with non-machine-learning methods to generate proof candidates for the holes. Then, CoqPilot checks if each proof candidate solves the given subgoal and, if successful, replaces the hole with it. The focus of CoqPilot is twofold. Firstly, we want to allow users to seamlessly combine multiple Coq generation approaches and provide a zero-setup experience for our tool. Secondly, we want to deliver a platform for LLM-based experiments on Coq proof generation. We developed a benchmarking system for Coq generation methods, available in the plugin, and conducted an experiment using it, showcasing the framework's possibilities. Demo of CoqPilot is available at: https://youtu.be/oB1Lx-So9Lo. Code at: https://github.com/JetBrains-Research/coqpilot