PROVE-RT: Generating Mechanized Theorem Prover Scripts for Real-Time Systems using LLMs

2026-08-12

AI Summary

Traditional schedulability analysis for real-time systems relies on manual proofs, which are difficult to scale, while mechanized verification approaches based on frameworks like PROSA or ROCQ, though rigorous, demand substantial domain expertise and extensive manual scripting. To address this challenge, this work proposes PROVE-RT, the first framework that integrates retrieval-augmented generation with a staged synthesis strategy to automatically produce mechanized proof scripts using large language models. PROVE-RT introduces dependency-aware informal sketches, a PROSA-specific corpus, and a staged skeleton-guided mechanism to significantly enhance generation quality. Experimental results demonstrate that PROVE-RT achieves a success rate of 44.7% on the evaluation benchmark, substantially outperforming mainstream large language models under direct prompting, thereby advancing the automation of schedulability analysis in real-time systems.

Abstract

Schedulability analysis is essential for certifying real-time systems, but existing tests are often developed through pen-and-paper proofs that are difficult to scale, validate, and maintain. Mechanized verification in PROSA/ROCQ offers a rigorous alternative, yet manually constructing such proofs requires substantial domain expertise and proof-engineering effort. Recent successes of large language models (LLMs) across a wide range of tasks make them promising candidates for generating PROSA/ROCQ scripts for mechanized theorem provers. However, state-of-the-art LLMs often lack the PROSA-specific knowledge required to correctly use its modeling abstractions and proof patterns. This paper introduces PROVE-RT, an LLM-assisted framework for generating PROSA/ROCQ scripts to mechanize schedulability analyses in real-time systems literature. PROVE-RT guides generation through dependency-aware informal sketches, retrieval from processed PROSA documentation, staged skeleton generation, and proof completion. We construct a mechanization-oriented corpus from 1, 191 real-time systems papers, containing 13, 134 informal sketches with dependency information. On a curated evaluation set, direct prompting of state-of-the-art LLMs fails to reliably generate valid PROSA mechanizations, whereas PROVE-RT achieves a success rate of 44.7%. These results show that retrieval-guided and staged LLM assistance can improve automated mechanization of schedulability analysis in PROSA/ROCQ.

Problem

• schedulability analysis
• real-time systems
• mechanized verification
• PROSA
• LLM-generated proofs

Innovation

• LLM-assisted mechanization
• schedulability analysis
• PROSA/ROCQ
• retrieval-augmented generation
• staged proof synthesis