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

• URL: http://arxiv.org/abs/2607.04092v1
• Date: Sun, 05 Jul 2026 03:07:10 GMT
• Title: SEDCoT: Enhancing LLM-Based COBOL Code Translation via Symbolic Execution and Delta Debugging
• Abstract summary: Maintenance is increasingly challenging due to outdated technologies, sparse documentation, and developer retirement.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.
• Score: 49.898541267264115
• License: http://creativecommons.org/licenses/by/4.0/
• 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 However, maintenance is increasingly challenging due to outdated technologies, sparse documentation, and developer retirement, necessitating code translation into modern languages like C. Traditional rule-based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.

Related papers

• CoSTAR: Data Synthesis-Driven Constraint-Aware COBOL Section Summarization for Legacy System Modernization [12.071793069280623]
  CoSTAR is an integrated framework that combines execution-validated data synthesis with constraint-aware training.<n>We evaluate CoSTAR on both public and confidential enterprise systems.
  arXiv  Detail & Related papers  (2026-09-10T10:08:46Z)
• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• LLM Based Long Code Translation using Identifier Replacement [3.833075202213095]
  We propose a novel zero-shot code translation method that incorporates identifier replacement.<n>By substituting user-given long identifiers with generalized placeholders during translation, our method improves the efficiency and cost-effectiveness of long code translation.
  arXiv  Detail & Related papers  (2025-10-10T06:28:15Z)
• Code Review Without Borders: Evaluating Synthetic vs. Real Data for Review Recommendation [37.86790434630698]
  Large Language Models (LLMs) are used to translate code changes from well-resourced languages into equivalent changes in underrepresented or emerging languages.<n>We compare the performance of these models against models trained on real labelled data.<n>This approach provides a scalable pathway to extend automated code review capabilities to rapidly evolving technology stacks.
  arXiv  Detail & Related papers  (2025-09-05T05:17:14Z)
• IFEvalCode: Controlled Code Generation [69.28317223249358]
  The paper introduces forward and backward constraints generation to improve the instruction-following capabilities of Code LLMs.<n>The authors present IFEvalCode, a multilingual benchmark comprising 1.6K test samples across seven programming languages.
  arXiv  Detail & Related papers  (2025-07-30T08:08:48Z)
• Type-Constrained Code Generation with Language Models [51.03439021895432]
  We introduce a type-constrained decoding approach that leverages type systems to guide code generation.<n>For this purpose, we develop novel prefix automata and a search over inhabitable types, forming a sound approach to enforce well-typedness on LLM-generated code.<n>Our approach reduces compilation errors by more than half and significantly increases functional correctness in code synthesis, translation, and repair tasks.
  arXiv  Detail & Related papers  (2025-04-12T15:03:00Z)
• ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation [57.604506522287814]
  Existing large language models (LLMs) only learn the contextual semantics of code during pre-training.<n>We propose ExeCoder to utilize executability representations such as functional semantics, syntax structures, and variable dependencies.<n>We show that ExeCoder achieves state-of-the-art performance in code translation, surpassing existing open-source code LLMs by over 10.88% to 38.78% and over 27.44% to 42.97% on two metrics.
  arXiv  Detail & Related papers  (2025-01-30T16:18:52Z)
• Semantic Alignment-Enhanced Code Translation via an LLM-Based Multi-Agent System [24.52067108242477]
  Code translation is crucial for software migration, system ablation, and cross-platform development.<n>Traditional rule-based methods rely on manually-written rules, which can be time-consuming and often result in less readable code.<n>More recently, the advance of Large Language Models (LLMs) further boosts learning-based code translation.<n>We propose a novel multi-agent system TRANSAGENT, which enhances LLM-based code translation by fixing the syntax errors and semantic errors.
  arXiv  Detail & Related papers  (2024-09-30T02:53:03Z)
• Guess & Sketch: Language Model Guided Transpilation [59.02147255276078]
  Learned transpilation offers an alternative to manual re-writing and engineering efforts. Probabilistic neural language models (LMs) produce plausible outputs for every input, but do so at the cost of guaranteed correctness. Guess & Sketch extracts alignment and confidence information from features of the LM then passes it to a symbolic solver to resolve semantic equivalence.
  arXiv  Detail & Related papers  (2023-09-25T15:42:18Z)
• 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)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.