[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83772-en":3,"doc-seo-83772-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},83772,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",6,"Technology","SEDCoT Enhancing LLM-Based COBOL Code Translation via Symbolic Execution and Delta Debugging","COBOL remains central to banking, insurance, and government infrastructure, yet modernization is hindered by outdated tooling, scarce documentation, and knowledge transfer loss. Traditional rule-based transcompilers generate outputs that are hard to read and maintain, while general-purpose LLM translation struggles with low-resource COBOL logic. SEDCoT combines LLM-driven initial translation, symbolic execution with LLM guidance for semantic discrepancy repair, and delta debugging to shrink failing tests into concise counterexamples. Evaluation shows ≥12% improvement and markedly higher readability versus rule-based baselines.","arXiv :2607 .04092v 1 [ cs . SE] 5 Jul 2026  \nSEDCoT: Enhancing LLM-Based COBOL Code Translation via Symbolic Execution and Delta Debugging  \nPHILLIP ENTIN∗ , University of Augsburg, TU Munich, LMU Munich, Germany WENCHAO GU∗†, Technical University of Munich, Germany  \nALEXANDER KNAPP, University of Augsburg, Germany CHUNYANG CHEN, Technical University of Munich, Germany  \nCOBOL 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 However, maintenance is increasingly challenging due to outdated technologies, sparse documentation, and developer retirement, necessitating code translation into modern languages like C. Traditional rule-based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 iterativelyrepair 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.  \nCCS Concepts: • Software and its engineering → Software maintenance tools; Source code generation;  \n• Computing methodologies → Machine translation.  \nAdditional KeyWords and Phrases: Code Translation, Code Repair, Large Language Model, Symbolic Execution, Delta Debugging  \nACM Reference Format:  \nPhillip Entin, Wenchao Gu, Alexander Knapp, and Chunyang Chen. 2018. SEDCoT: Enhancing LLM-Based COBOL Code Translation via Symbolic Execution and Delta Debugging. In Proceedings of Make sure to enter the correct conference title from your rights confirmation email (Conference acronym ’XX). ACM, New York, NY, USA, 24 pages. [https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \n1 Introduction  \nLegacy systems remain critical across many sectors, including banking, insurance, and government infrastructure [56] . Despite their age, these systems continue to support mission-critical operations—processing $3 trillion in commerce transactions every day [8] . However, maintaining them is increasingly difficult due to outdated technologies, sparse digital documentation, and the retirement  \n∗ Both authors contributed equally to this work.  \n†Corresponding author.  \nAuthors’ Contact Information: Phillip Entin, [p.entin@tum.de](p.entin@tum.de), University of Augsburg, TU Munich, LMU Munich, Germany; Wenchao Gu, [wenchao.gu@tum.de](wenchao.gu@tum.de), Technical University of Munich, Germany; Alexander Knapp, alexander.knapp@uni-a.de, University of Augsburg, Germany; Chunyang Chen, [chun-yang.chen@tum.de](chun-yang.chen@tum.de), Technical University of Munich, Germany.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires [prior specific permission and/or a fee. Request permissions from permissions@acm.org](prior specific permission and/or a fee. Request permissions from permissions@acm.org).  \nConference acronym ’XX, Woodstock, NY  \n© 2018 Copyright held by the owner/author(s) . Publication rights licensed to ACM.  \nACM ISBN 978-1-4503-XXXX-X/2018/06  \n[https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX","cbCaiuyvNI9OvgxN","https://ap.wps.com/l/cbCaiuyvNI9OvgxN","pdf",915020,1,24,"English","en",105,"# Introduction\n## Challenges in legacy system modernization\n## Semantic gap between COBOL and mainstream languages\n## Limitations of rule-based and generic LLM translation\n# SEDCoT Framework\n## LLM-based initial translation\n## Symbolic execution with LLM guidance\n## Delta debugging for succinct counterexamples\n# Evaluation and Results","[{\"question\":\"What is SEDCoT and what problem does it address?\",\"answer\":\"SEDCoT is a COBOL-to-C code translation framework designed to improve correctness and maintainability when migrating legacy COBOL systems. It targets the readability issues of rule-based transcompilers and the suboptimal correctness of generic LLM translation for COBOL’s distinct logic patterns.\"},{\"question\":\"How does SEDCoT improve translation correctness beyond initial LLM output?\",\"answer\":\"SEDCoT first performs initial translation using LLMs, then uses symbolic execution combined with LLM guidance to generate test suites and iteratively repair semantic discrepancies. This workflow helps align translated behavior with the original COBOL semantics.\"},{\"question\":\"What role does delta debugging play in SEDCoT’s process?\",\"answer\":\"Delta debugging minimizes failing tests into succinct counterexamples, making automated code repair faster. By reducing the size of failing evidence, it accelerates the refinement loop for translation fixes.\"}]",1784190319,60,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"sedcot-enhancing-llm-based-cobol-code-translation-via-symbolic-execution-and-delta-debugging","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/technology/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/sedcot-enhancing-llm-based-cobol-code-translation-via-symbolic-execution-and-delta-debugging/83772/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is SEDCoT and what problem does it address?","Question",{"text":75,"@type":76},"SEDCoT is a COBOL-to-C code translation framework designed to improve correctness and maintainability when migrating legacy COBOL systems. It targets the readability issues of rule-based transcompilers and the suboptimal correctness of generic LLM translation for COBOL’s distinct logic patterns.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does SEDCoT improve translation correctness beyond initial LLM output?",{"text":80,"@type":76},"SEDCoT first performs initial translation using LLMs, then uses symbolic execution combined with LLM guidance to generate test suites and iteratively repair semantic discrepancies. This workflow helps align translated behavior with the original COBOL semantics.",{"name":82,"@type":73,"acceptedAnswer":83},"What role does delta debugging play in SEDCoT’s process?",{"text":84,"@type":76},"Delta debugging minimizes failing tests into succinct counterexamples, making automated code repair faster. By reducing the size of failing evidence, it accelerates the refinement loop for translation fixes.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,109,112,117,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":28,"slug":108},5,"Comic","comic",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":110,"slug":111},50,"technology",{"id":113,"doc_module":4,"doc_module_name":45,"category_name":114,"show_sort_weight":115,"slug":116},7,"Healthcare",40,"healthcare",{"id":118,"doc_module":4,"doc_module_name":45,"category_name":119,"show_sort_weight":120,"slug":121},8,"Research & Report",30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]