SEDCoT: Enhancing LLM-Based COBOL Code Translation via Symbolic Execution and Delta Debugging

2026-07-04

AI Summary

This work addresses the challenges of low correctness and poor readability in automatically translating COBOL to modern languages like C, stemming from COBOL’s scarcity of resources and idiosyncratic logic. The authors propose SEDCoT, a novel framework that integrates symbolic execution and incremental debugging into a large language model (LLM)-driven translation pipeline. SEDCoT first leverages an LLM to produce an initial translation, then iteratively detects and corrects semantic discrepancies by collaboratively generating test cases through symbolic execution and the LLM. Failed tests are streamlined via incremental debugging to accelerate repair. Evaluated on a public COBOL-to-C dataset, SEDCoT improves translation correctness by at least 12% over the current state-of-the-art and yields significantly more readable code than rule-based approaches.

Abstract

COBOL remains critical across banking, insurance, and government infrastructure. However, maintenance is increasingly challenging due to outdated technologies, sparse documentation, and developer retirement, necessitating code translation into modern languages like C. Traditional rule-based transcompilers yield outputs that are difficult to read and maintain, while general-purpose large language models (LLMs) achieve suboptimal correctness because COBOL is a low-resource language with distinct logic patterns. To bridge this gap, we propose SEDCoT, a novel COBOL-to-C translation framework. SEDCoT first leverages LLMs for initial translation, then combines symbolic execution with LLM guidance to generate test suites and iteratively repair semantic discrepancies. Finally, it integrates delta debugging to minimize failing tests into succinct counterexamples, accelerating automated code repair. Evaluating SEDCoT on a public COBOL-to-C dataset demonstrates that it outperforms state-of-the-art baselines by at least 12% while producing translations with substantially higher readability than rule-based alternatives.

Problem

• COBOL translation
• code migration
• legacy systems
• LLM-based translation
• semantic correctness

Innovation

• Symbolic Execution
• Delta Debugging
• LLM-guided Translation
• COBOL-to-C Translation
• Automated Code Repair