一句话:提出 CoqPilot:一个 VS Code 插件,结合 LLM 与传统方法自动填补 Coq 证明空洞,并提供基准测试平台。
CoqPilot 旨在自动化 Coq 证明写作。该插件收集 Coq 文件中由 admit 标记的证明空洞,结合 LLM 与非机器学习方法为每个空洞生成候选证明,并交由 Coq 检查;若候选证明成功求解子目标,则替换原有空洞。CoqPilot 强调无缝组合多种 Coq 证明生成方法、提供零配置使用体验,并作为 LLM 在 Coq 证明生成上的实验平台。作者还实现了内置的基准测试系统,并开展实验展示框架能力,同时提供演示视频与开源代码。
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