COBOLAssist: Analyzing and Fixing Compilation Errors for LLM-Powered COBOL Code Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908937347923968 |
|---|---|
| author | Dau, Anh T. V. Tan, Shin Hwei Yang, Jinqiu Bui, Nghi D. Q. Nguyen, Anh Tuan |
| author_facet | Dau, Anh T. V. Tan, Shin Hwei Yang, Jinqiu Bui, Nghi D. Q. Nguyen, Anh Tuan |
| contents | Legacy programming languages such as COBOL (Common Business-Oriented Language) remain critical in business computing. However, maintaining legacy COBOL systems is increasingly challenging due to a declining pool of skilled developers and the persistence of COBOL errors that require deep domain expertise to resolve. This paper investigates the challenges of COBOL compilation errors and introduces a framework leveraging large language models (LLMs) to address these issues. We first categorize the common compilation errors in LLM-generated COBOL code into three groups: incomplete code errors, syntax errors, and type-related errors. We further propose COBOLAssist, a technique to enhance code correctness through iterative repairs guided by compilation feedback. Our evaluation using five LLMs including GPT variants and mAInframer, shows a high prevalence of incorrect program structures and function usage in COBOL programs and demonstrates the effectiveness of COBOLAssist, with the compilation success rates increasing from 29.5\% to 64.38\% for GPT-4o-mini and from 41.8\% to 95.89\% for GPT-4o. It also improves pass@1 significantly, for example from 9.1 to 22.6 for GPT-4. Notably, while mAInframer-34B achieves the highest compilation success rate, its functional correctness remains limited. This research not only highlights the limitations in current LLMs for COBOL but also demonstrates a practical path forward for automated debugging in legacy systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03978 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | COBOLAssist: Analyzing and Fixing Compilation Errors for LLM-Powered COBOL Code Generation Dau, Anh T. V. Tan, Shin Hwei Yang, Jinqiu Bui, Nghi D. Q. Nguyen, Anh Tuan Software Engineering Programming Languages Legacy programming languages such as COBOL (Common Business-Oriented Language) remain critical in business computing. However, maintaining legacy COBOL systems is increasingly challenging due to a declining pool of skilled developers and the persistence of COBOL errors that require deep domain expertise to resolve. This paper investigates the challenges of COBOL compilation errors and introduces a framework leveraging large language models (LLMs) to address these issues. We first categorize the common compilation errors in LLM-generated COBOL code into three groups: incomplete code errors, syntax errors, and type-related errors. We further propose COBOLAssist, a technique to enhance code correctness through iterative repairs guided by compilation feedback. Our evaluation using five LLMs including GPT variants and mAInframer, shows a high prevalence of incorrect program structures and function usage in COBOL programs and demonstrates the effectiveness of COBOLAssist, with the compilation success rates increasing from 29.5\% to 64.38\% for GPT-4o-mini and from 41.8\% to 95.89\% for GPT-4o. It also improves pass@1 significantly, for example from 9.1 to 22.6 for GPT-4. Notably, while mAInframer-34B achieves the highest compilation success rate, its functional correctness remains limited. This research not only highlights the limitations in current LLMs for COBOL but also demonstrates a practical path forward for automated debugging in legacy systems. |
| title | COBOLAssist: Analyzing and Fixing Compilation Errors for LLM-Powered COBOL Code Generation |
| topic | Software Engineering Programming Languages |
| url | https://arxiv.org/abs/2604.03978 |