Related papers: Code Reborn AI-Driven Legacy Systems Modernization from COBOL to Java

Related papers

SEDCoT: Enhancing LLM-Based COBOL Code Translation via Symbolic Execution and Delta Debugging [49.898541267264115]
Maintenance is increasingly challenging due to outdated technologies, sparse documentation, and developer retirement.<n>Traditional rule-based transcompilers yield outputs that are difficult to read and maintain.<n>We propose SEDCoT, a novel-to-C translation framework.
arXiv Detail & Related papers (2026-07-05T03:07:10Z)
COBOL-Coder: Domain-Adapted Large Language Models for COBOL Code Generation and Translation [10.733306714499067]
Existing large language models (LLMs) struggle to generate and translate code correctly.<n>We introduce an automated data curation pipeline that combines compiler-guided validation with multi-stage similarity-based filtering.<n>Code-Coder achieves up to 73.95 percent compilation success rate and 49.33 Pass-1 onEval, compared to 41.8 percent and 16.4 for GPT-4o.
arXiv Detail & Related papers (2026-04-05T06:12:49Z)
COBOLAssist: Analyzing and Fixing Compilation Errors for LLM-Powered COBOL Code Generation [10.733306714499067]
This paper investigates the challenges of compilation errors and introduces a framework leveraging large language models (LLMs) to address these issues.<n>We first categorize the common compilation errors in LLM-generated code into three groups: incomplete code errors, syntax errors, and type-related errors.
arXiv Detail & Related papers (2026-04-05T05:51:54Z)
InCoder-32B: Code Foundation Model for Industrial Scenarios [95.28947955949296]
We introduce InCoder-32B (Industrial-Coder-32B) to unify code intelligence across chip design, GPU kernel optimization, embedded systems, compiler optimization, and 3D modeling.<n>InCoder-32B achieves highly competitive performance on general tasks while establishing strong open-source baselines across industrial domains.
arXiv Detail & Related papers (2026-03-17T17:01:35Z)
Evaluating perturbation robustnessof generative systems that use COBOL code inputs [1.3327839779221817]
Systems incorporating large language models (LLMs) as a component are known to be sensitive (i.e., non-robust) to minor input variations.<n>Here, we present a framework to evaluate robustness of systems using code as input.
arXiv Detail & Related papers (2025-11-23T15:16:08Z)
EvoGraph: Hybrid Directed Graph Evolution toward Software 3.0 [0.0]
We introduce **EvoGraph**, a framework that enables software systems to evolve their own source code, build pipelines, documentation, and tickets.<n>EvoGraph fixes 83% of known security vulnerabilities, translates to Java with 93% functional equivalence, and maintains documentation freshness within two minutes.<n>We extend our approach to **evoGraph**, leveraging language-specific SLMs for modernizing.NET, Lisp, CGI, ColdFusion, legacy Python, and Cs.
arXiv Detail & Related papers (2025-08-07T09:36:30Z)
Enhancing COBOL Code Explanations: A Multi-Agents Approach Using Large Language Models [1.835291631794229]
We propose a multi-agent approach that generates explanations for functions, files, and the overall project.<n>We evaluate the effectiveness of our approach using 14 open-source, real-world projects.
arXiv Detail & Related papers (2025-07-02T22:28:35Z)
Automated Validation of COBOL to Java Transformation [5.162381960073761]
We propose a framework and a tool to help validate the equivalence of and translated Java.<n>The results can also help repair the code if there are some issues and provide feedback to the AI model to improve.
arXiv Detail & Related papers (2025-04-14T06:13:32Z)
Automated Testing of COBOL to Java Transformation [5.395038658302793]
We develop a testing framework for IBM Watsonx Code Assistant for Z (WCA4Z) [5], an industrial tool designed for Java translation.<n>Our framework uses symbolic execution to generate unit tests for mocking external calls and transforming them into JUnit tests to validate semantic equivalence with translated Java.
arXiv Detail & Related papers (2025-04-14T04:53:30Z)
RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph [63.87660059104077]
We present RepoGraph, a plug-in module that manages a repository-level structure for modern AI software engineering solutions. RepoGraph substantially boosts the performance of all systems, leading to a new state-of-the-art among open-source frameworks.
arXiv Detail & Related papers (2024-10-03T05:45:26Z)
CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution [50.7413285637879]
The CRUXEVAL-X code reasoning benchmark contains 19 programming languages. It comprises at least 600 subjects for each language, along with 19K content-consistent tests in total. Even a model trained solely on Python can achieve at most 34.4% Pass@1 in other languages.
arXiv Detail & Related papers (2024-08-23T11:43:00Z)
MapCoder: Multi-Agent Code Generation for Competitive Problem Solving [3.3856216159724983]
We introduce a new approach to code generation tasks leveraging multi-agent prompting. Our framework, MapCoder, consists of four LLM agents specifically designed to emulate the stages of program synthesis. Our method consistently delivers superior performance across various programming languages.
arXiv Detail & Related papers (2024-05-18T22:10:15Z)
OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement [58.034012276819425]
We introduce OpenCodeInterpreter, a family of open-source code systems for generating, executing, and iteratively refining code.<n>Our comprehensive evaluation of OpenCodeInterpreter across key benchmarks such as HumanEval, MBPP, and their enhanced versions from EvalPlus reveals its exceptional performance.
arXiv Detail & Related papers (2024-02-22T16:06:23Z)
X-COBOL: A Dataset of COBOL Repositories [4.8342038441006805]
We constructed a dataset of 84 repositories mined from GitHub, containing rich metadata on the development cycle of the projects. Our dataset also provides 1255 files present inside the mined repositories.
arXiv Detail & Related papers (2023-06-08T02:42:09Z)
Neuro-symbolic Zero-Shot Code Cloning with Cross-Language Intermediate Representation [13.881954273779403]
We define a neuro-symbolic approach to address the task of finding semantically similar clones for the codes of the legacy programming language, without training data. We fine-tune UnixCoder, the best-performing model for cross-programming language search, for the Code Cloning task with the SBT IRs of C code-pairs, available in the CodeNet dataset. With this fine-tuned UnixCoder, we get a performance improvement of 12.85 MAP@2 over the pre-trained UniXCoder model, in a zero-shot setting, on the test split synthesized from the CodeNet
arXiv Detail & Related papers (2023-04-26T07:41:26Z)
CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X [50.008474888951525]
We introduce CodeGeeX, a multilingual model with 13 billion parameters for code generation. CodeGeeX is pre-trained on 850 billion tokens of 23 programming languages.
arXiv Detail & Related papers (2023-03-30T17:34:01Z)
ReACC: A Retrieval-Augmented Code Completion Framework [53.49707123661763]
We propose a retrieval-augmented code completion framework, leveraging both lexical copying and referring to code with similar semantics by retrieval. We evaluate our approach in the code completion task in Python and Java programming languages, achieving a state-of-the-art performance on CodeXGLUE benchmark.
arXiv Detail & Related papers (2022-03-15T08:25:08Z)
CoSQA: 20,000+ Web Queries for Code Search and Question Answering [63.92224685262063]
CoSQA dataset includes 20,604 labels for pairs of natural language queries and codes. We introduce a contrastive learning method dubbed CoCLR to enhance query-code matching. We show that evaluated on CodeXGLUE with the same CodeBERT model, training on CoSQA improves the accuracy of code question answering by 5.1%.
arXiv Detail & Related papers (2021-05-27T15:37:21Z)
Project CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks [11.10732802304274]
Project CodeNet consists of 14M code samples and about 500M lines of code in 55 different programming languages. Project CodeNet is not only unique in its scale, but also in the diversity of coding tasks it can help benchmark.
arXiv Detail & Related papers (2021-05-25T00:13:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.