Agentic Method for Deterministic Validation of Legacy Code Migration

• URL: http://arxiv.org/abs/2607.28271v1
• Date: Thu, 30 Jul 2026 14:25:23 GMT
• Title: Agentic Method for Deterministic Validation of Legacy Code Migration
• Abstract summary: "Locksmith Loop" is initiated by preparing two runtime environments.<n>"Locksmith Loop" performs Witness Search over input mocks to penetrate program branches, followed by parity-preserving mutations.<n> Locksmith consistently improved coverage beyond input-search plateaus.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Migration of legacy COBOL programs to Java requires extensive testing to ensure correct functionality. This effort is often complicated by the lack of test data and the difficulty of validating all corner cases. In this paper we propose a novel agentic test-synthesis method, the "Locksmith Loop," which is initiated by preparing two runtime environments: the COBOL source and the generated Java target are each instrumented with mocks and executed off-mainframe on commodity hardware, then an iterative agentic loop performs Witness Search over input mocks to penetrate program branches, followed by parity-preserving mutations. When routing boundaries are reached, an analyzer identifies a Locked Paragraph: a condition preventing deeper exploration. Across three COBOL-Java case studies, spanning two open-source programs and one internal production-like COBOL program and ranging from 430 to 4,114 source lines, Locksmith consistently improved coverage beyond input-search plateaus, reaching nearly complete coverage on the two open-source programs and 91.90% branch coverage on the internal production-like COBOL program. The generated Java matched the COBOL reference under deterministic parity checks in all accepted test cases. Through these findings we demonstrate, to the best of our knowledge, a novel approach for validating agentic coding output using a deterministic oracle.

Related papers

• Technical Report: A Formal Semantics for Java Symbolic Evaluation using Large-Block Encoding [0.9985222473972001]
  Symbolic execution is used to find bugs, generate test cases, and provide correctness guarantees.<n>Java Ranger is a path-merging tool for Java programs that progressively transforms imperative Java code toward the language of formal logic.<n>We formalize each of these transformations and prove their soundness with respect to a simplified version of the Java concrete semantics.
  arXiv  Detail & Related papers  (2026-08-05T06:49:28Z)
• 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)
• RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories [58.32028251925354]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, but their proficiency in producing secure code remains a critical, under-explored area.<n>We introduce RealSec-bench, a new benchmark for secure code generation meticulously constructed from real-world, high-risk Java repositories.
  arXiv  Detail & Related papers  (2026-01-30T08:29:01Z)
• CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment [98.87395842351627]
  Large Language Models (LLMs) excel at code generation by learning from vast code corpora.<n>A fundamental semantic gap remains between their training on textual patterns and the goal of functional correctness.<n>We propose CodeRL+, a novel approach that integrates execution semantics alignment into the RLVR training pipeline for code generation.
  arXiv  Detail & Related papers  (2025-10-21T09:48:06Z)
• Exposing Go's Hidden Bugs: A Novel Concolic Framework [2.676686591720132]
  We present Zorya, a novel methodology to evaluate Go programs comprehensively.<n>By systematically exploring execution paths to uncover vulnerabilities beyond conventional testing, symbolic execution offers distinct advantages.<n>Our solution employs Ghidra's P-Code as an intermediate representation (IR)
  arXiv  Detail & Related papers  (2025-05-26T16:26:20Z)
• 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)
• Evolutionary Generative Fuzzing for Differential Testing of the Kotlin Compiler [14.259471945857431]
  We investigate the effectiveness of differential testing in finding bugs within the Kotlin compilers developed at JetBrains. We propose a black-box generative approach that creates input programs for the K1 and K2 compilers. Our case study shows that the proposed approach effectively detects bugs in K1 and K2; these bugs have been confirmed and (some) fixed by JetBrains developers.
  arXiv  Detail & Related papers  (2024-01-12T16:01:12Z)
• ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers [60.6418431624873]
  Large language models (LLMs) excel at implementing code from functionality descriptions but struggle with algorithmic problems. We propose ALGO, a framework that synthesizes Algorithmic programs with LLM-Generated Oracles to guide the generation and verify their correctness. Experiments show that when equipped with ALGO, we achieve an 8x better one-submission pass rate over the Codex model and a 2.6x better one-submission pass rate over CodeT.
  arXiv  Detail & Related papers  (2023-05-24T00:10:15Z)
• Improved Tree Search for Automatic Program Synthesis [91.3755431537592]
  A key element is being able to perform an efficient search in the space of valid programs. Here, we suggest a variant of MCTS that leads to state of the art results on two vastly different DSLs.
  arXiv  Detail & Related papers  (2023-03-13T15:09:52Z)
• LEVER: Learning to Verify Language-to-Code Generation with Execution [64.36459105535]
  We propose LEVER, a simple approach to improve language-to-code generation by learning to verify the generated programs with their execution results. Specifically, we train verifiers to determine whether a program sampled from the LLMs is correct or not based on the natural language input, the program itself and its execution results. LEVER consistently improves over the base code LLMs(4.6% to 10.9% with code-davinci) and achieves new state-of-the-art results on all of them.
  arXiv  Detail & Related papers  (2023-02-16T18:23:22Z)
• Natural Language to Code Translation with Execution [82.52142893010563]
  Execution result--minimum Bayes risk decoding for program selection. We show that it improves the few-shot performance of pretrained code models on natural-language-to-code tasks.
  arXiv  Detail & Related papers  (2022-04-25T06:06:08Z)

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.