Retrieval-Augmented TLAPS Proof Generation with Large Language Models

Abstract: We present a novel approach to automated proof generation for the TLA+ Proof System (TLAPS) using LLMs. Our method combines two key components: a sub-proof obligation generation phase that breaks down complex proof obligations into simpler sub-obligations, and a proof generation phase that leverages Retrieval-Augmented Generation with verified proof examples. We evaluate our approach using proof obligations from varying complexity levels of proof obligations, spanning from fundamental arithmetic properties to the properties of algorithms. Our experiments demonstrate that while the method successfully generates valid proofs for intermediate-complexity obligations, it faces limitations with more complex theorems. These results indicate that our approach can effectively assist in proof development for certain classes of properties, contributing to the broader goal of integrating LLMs into formal verification workflows.