Automatic Syntax Error Repair for Discrete Controller Synthesis using Large Language Model

2025-12-08

AI Summary

Discrete controller synthesis (DCS) suffers from slow development cycles due to modeling errors stemming from the steep syntactic learning curve of formal specification languages (e.g., FSP, FLNL). This paper introduces the first LLM-based automated repair method targeting syntax errors in DCS. Our approach leverages domain knowledge to design a tripartite prompting strategy—integrating syntactic rules, error patterns, and expert-crafted examples—to embed formal semantic priors into LLM reasoning. Evaluated on a novel, manually curated benchmark comprising real-world syntax errors, our method achieves an 89.7% repair accuracy and operates 3.46× faster than human experts, significantly outperforming general-purpose code repair models. All code, data, and prompt templates are publicly released, establishing a reusable technical pathway toward practical adoption of formal methods.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Discrete Controller Synthesis (DCS) is a powerful formal method for automatically generating specifications of discrete event systems. However, its practical adoption is often hindered by the highly specialized nature of formal models written in languages such as FSP and FLTL. In practice, syntax errors in modeling frequently become an important bottleneck for developers-not only disrupting the workflow and reducing productivity, but also diverting attention from higher-level semantic design. To this end, this paper presents an automated approach that leverages Large Language Models (LLMs) to repair syntax errors in DCS models using a well-designed, knowledge-informed prompting strategy. Specifically, the prompting is derived from a systematic empirical study of common error patterns, identified through expert interviews and student workshops. It equips the LLM with DCS-specific domain knowledge, including formal grammar rules and illustrative examples, to guide accurate corrections. To evaluate our method, we constructed a new benchmark by systematically injecting realistic syntax errors into validated DCS models. The quantitative evaluation demonstrates the high effectiveness of the proposed approach in terms of repair accuracy and its practical utility regarding time, achieving a speedup of 3.46 times compared to human developers. The experimental replication suite, including the benchmark and prompts, is available at https://github.com/Uuusay1432/DCSModelRepair.git

Problem

• Automated syntax error repair for Discrete Controller Synthesis models
• Leveraging Large Language Models with domain-specific prompting strategies
• Improving developer productivity by accelerating error correction processes

Innovation

• Leverages Large Language Models for automated syntax error repair
• Uses knowledge-informed prompting derived from common error patterns
• Achieves 3.46 times speedup compared to human developers