ISCSR Research Publishing
Journal of Adaptive Data and Algorithmic Intelligence
Research Article Published October 9, 2026 Article jadai20260012

Compiler-Guided Legacy Code Translation for Maintainable Software Migration

Read & download PDF
Abstract

Legacy software migration remains difficult because old systems often contain undocumented business rules, obsolete library calls, implicit data formats, and tightly coupled procedures. Large language models can translate code between programming languages, but direct translation may change program behavior, introduce hidden runtime errors, or produce code that is hard to maintain. This study investigates compiler-guided legacy code translation for software migration. We propose TransAgent, a multi-agent translation model with a program slicing agent, a semantic translation agent, a compiler feedback agent, a behavior equivalence agent, and a refactoring agent. The program slicing agent separates legacy modules into control-flow units, data-processing units, and external-interface units. The semantic translation agent converts source code into target-language implementations while preserving variable dependencies and exception logic. The compiler feedback agent identifies syntax errors, type mismatches, unreachable code, and missing libraries. The behavior equivalence agent compares outputs between legacy and translated versions using regression tests and generated boundary cases. The refactoring agent improves naming consistency, modular structure, exception handling, and dependency clarity. The empirical study focused on enterprise migration from legacy Java and procedural Python scripts to modern Java and TypeScript services. The dataset contained 186 modules from inventory, billing, customer service, and reporting systems, with 214,000 lines of source code and 3,420 archived change requests. Instead of only measuring pass rates, the study also measured migration effort, behavior preservation, and maintainability. TransAgent preserved reference outputs in 88.6% of migrated modules after two repair rounds, compared with 71.9% for direct LLM translation. The number of manual correction hours decreased from 2.8 hours to 1.4 hours per thousand lines of code. The maintainability index increased by 16.2 points on average, and circular dependencies were reduced by 31.5%. In modules involving financial calculation rules, numerical deviation was kept below 0.1% in 94.3% of test cases. The results indicate that compiler feedback and behavior-equivalence checking can make automated code translation more suitable for real software migration.

Keywords
Code translationlegacy software migrationcompiler feedbackbehavior equivalenceprogram repairmaintainabilitymulti-agent systems
References
  1. Wu, C., & Chen, H. (2025). Research on system service convergence architecture for AR/VR system.
  2. Mini Han Wang , " AI-Powered Innovations in Ophthalmic Diagnosis and Treatment ", Bentham Science Publishers (2025). https://doi.org/10.2174/97988988122871250101.
  3. Zheng, J., & Makar, M. (2022). Causally motivated multi-shortcut identification and removal. Advances in Neural Information Processing Systems, 35, 12800-12812.
  4. Xu, D., Gui, H., & Chen, H. (2026, March). Research on Layered Control and Fault Recovery Mechanisms for Fast Charging Safety Diagnosis of High-Voltage Battery Systems Under Charging Network Interoperability Conditions. In 2026 3rd International Conference on Electrical Technology and Automation Engineering (ETAE) (pp. 669-672). IEEE.
  5. Quan, Q., Gao, Y., & Wang, Q. (2025). The impact of teacher emotional support on students' engagement in AI-mediated English learning environments: The mediating role of resilience and self-efficacy. Acta Psychologica, 260, 105766.
  6. Zhang, Z. (2026). A Study on the Impact of Cost Presentation on Decision-making Bias and Cancellation Behavior in Online Subscriptions. Available at SSRN 7349839.
  7. Qi, C., & Qiao, X. (2026). Building and Operating a Large Scale Multi-Agent System: A Case Study from Industry. Available at SSRN 6795198.
  8. Du, Y., Liu, Q., Dong, Y., & Chen, Z. (2026). Cross-Domain Transfer and Few-Shot Recognition of Defect Images in Complex Industrial Settings.
  9. Wang, Z., Yu, J., Liu, H., Zheng, Z., Jin, Y., Li, S., ... & Zhang, K. (2025, July). Generative Music Models’ Alignment with Professional and Amateur Users’ Expectations. In Findings of the Association for Computational Linguistics: ACL 2025 (pp. 6909-6920).
  10. Xiong, W., Guo, Y., & Zeng, Y. (2026). A Study on the Energy Efficiency of MEP Systems and Coordinated Dispatch Mechanisms for Multi-energy Systems in High-density Urban Buildings. Available at SSRN 7120518.
  11. Zhao, J., Fan, J., & Li, L. (2026). A Study on an Explainable Causal-Enhanced LLM Agent for Predicting the Forming Quality of Automotive Component Materials.
  12. Jiao, Y., Shi, T., Zhao, B., & Wang, A. (2026). Retrieval-Guided Structured Reasoning and Interpretable Representation Learning for Large-Scale Video–Language Models.
  13. Xu, Y., Cui, J., Zhu, Z., Shang, H., Luan, S., Xu, M., ... & Zhu, S. (2026). Wam-flow: Parallel coarse-to-fine motion planning via discrete flow matching for autonomous driving. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 24918-24928).
  14. Liang, S., Du, Y., Chen, W., & Liu, Z. (2026). Order Allocation and Emergency Transportation Decisions Amid Multi-Source Procurement Disruptions.
  15. Hong, Z., Liang, S., Xu, T., & Chen, H. (2026). A Study on Failover Verification and Recovery Objective Prediction for Cross-Region Cloud Services.
  16. Huang, J., Yin, J., Xu, T., & Yang, J. (2026). Quality Assessment and User Adoption Prediction for Enterprise-Level Financial Reporting Data Products. Available at SSRN 7179118.
  17. Zheng, X., Chen, X., Gong, S., Griffin, X., & Slabaugh, G. (2025, September). Xfmamba: Cross-fusion mamba for multi-view medical image classification. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 672-682). Cham: Springer Nature Switzerland.
  18. Zhang, Z., Wang, J., Li, Z., Wang, Y., & Zheng, J. (2025). Anncoder: A mti-agent-based code generation and optimization model. Symmetry, 17(7), 1087.
  19. Liang, S., Hsu, K. H., & Liu, Z. (2026). Rolling Scheduling and Capacity Balancing for Server Assembly Under Engineering Change Disturbances.
  20. Bao, Y., & Wang, H. (2026). Large-scale Metrics Migration: A Systematic Approach to Rebuilding Production Measurement Infrastructure. Available at SSRN 7185660.
  21. Su, J., He, C., Zhu, F., Xu, X., Guan, D., & Si, C. (2024, September). Hpff: Hierarchical locally supervised learning with patch feature fusion. In European Conference on Computer Vision (pp. 293-309). Cham: Springer Nature Switzerland.
  22. Zhao, Z., & Welsch, R. E. (2026). Point-in-Time Financial RAG with Frozen LLMs and Market-Feedback Adaptive Retrieval. arXiv preprint arXiv:2605.31201.
  23. Yuan, Y., Huang, J., Yin, J., & Xu, T. (2026). Confidence Calibration and Semantic Error Analysis for Ambiguous Coreference Resolution in User-generated Social Media Text. Available at SSRN 7393238.
  24. Lyu, Y. (2025). Enhancing Approximate Conformance Checking Accuracy with Hierarchical Clustering Model Behaviour Sampling. International Journal of Advanced Computer Science & Applications, 16(8).
  25. Bao, Y., & Wang, H. (2026). Orion: A High-Throughput, Fault-Tolerant Event Routing Architecture for Hyperscale Data Streams. Fault-Tolerant Event Routing Architecture for Hyperscale Data Streams (January 01, 2026).
  26. Chaoyong Ma, Nan Si, Xuewei Song, Chen Liang and Haoming Luo, A Bearing Fault Diagnosis Method Based on Concise Empirical Wavelet Transform, International Journal of Comprehensive Engineering，2023, 12(1), 1-6
  27. Wang, S., Feng, Y., & Fang, X. (2026, May). A Large Language Model-Enabled Multi-Agent Collaboration Method for Complex Task Solving. In 2026 6th International Symposium on Computer Technology and Information Science (ISCTIS) (pp. 253-256). IEEE.
  28. Liang, J., Xiao, Y., Yang, H., Yu, Z., Liu, J. N., & Yang, K. (2026, April). C-HyPOD: Causal Hyperbolic Representation Learning with Prototype Orthogonal Disentanglement for Graph Out-of-Distribution Recommendation. In Proceedings of the ACM Web Conference 2026 (pp. 6541-6550).
  29. Xi, X., Chen, P., Qiu, Y., Luo, R., Tong, P., & Liang, J. Video-BCI: Bayesian Cognitive Integration of Self-Prior Hypotheses for Video Understanding. In Forty-third International Conference on Machine Learning.
  30. Yang, Q., & Du, Y. (2026). Predicting Rollback Risks and Controlling Gradual Rollout Traffic for Online Ranking Feature Deployments.
  31. Xu, Z., Zhang, X., Li, R., Tang, Z., Huang, Q., & Zhang, J. (2024). Fakeshield: Explainable image forgery detection and localization via multi-modal large language models. arXiv preprint arXiv:2410.02761.
  32. Huang, Q., Xu, Z., Zhang, X., & Zhang, J. (2025). UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization. arXiv preprint arXiv:2510.03161.
  33. Jiang, C. (2026). Information doesn’t work? Testing experiential drivers of VR application in heritage tourism by affective-cognitive pathways. Journal of Hospitality and Tourism Technology, 1-28.
  34. Yuan, Y., Yin, J., Huang, J., & Xu, T. (2026). Weakly Supervised Anomaly Detection and Privacy Risk Scoring in Community Message Threads.
  35. Xi Qiao, Di Zhao, Nan Si, Jifeng Sui and Yonggang Xu, Weighting Spectrum Editing Based on Amplitude Mapping and Its Application in Composite Fault Diagnosis of Rolling Bearings, International Journal of Comprehensive Engineering，2024, 13(1), 13-21
  36. Xu, Z., Zhang, X., Zhou, X., & Zhang, J. (2025). AvatarShield: Visual Reinforcement Learning for Human-Centric Video Forgery Detection. arXiv preprint arXiv:2505.15173.
  37. Wang, T., & Xia, Z. (2025). Stability of In-Context Learning: A Spectral Coverage Perspective. arXiv preprint arXiv:2509.20677.
  38. Liu, T., He, J., Zhou, R., Song, J., Liu, H., & Liang, Y. (2025). Revolutionizing clinical decision making through deep learning and topic modeling for pathway optimization. Scientific Reports, 15(1), Article 28787. https://doi.org/10.1038/s41598-025-12679-z
  39. Wu, X., Xing, X., Yao, J., Qian, Q., & Song, J. (2025). Scnet: spectral convolutional networks for multivariate time series classification. Applied Intelligence, 55(6), Article 456. https://doi.org/10.1007/s10489-025-06352-1
  40. Xixin Chen, Ming Tu, Lei Su and Ke Li, Rolling Bearing Fault Diagnosis Based on Digital Twin Method, International Journal of Comprehensive Engineering，2024, 13(1), 22-39
  41. Ma, C., Song, J., Xu, Y., Fan, H., Wu, X., & Sun, T. (2024). Vehicle-Based Machine Vision Approaches in Intelligent Connected System. IEEE Transactions on Intelligent Transportation Systems, 25(3), 2827-2836. https://doi.org/10.1109/TITS.2023.3276325
  42. Bing Wang, Haihong Tang, Xiaojia Zu and Wuwei Feng, Application of Parameter Adaptive VMD in Bearing Fault Diagnosis, International Journal of Comprehensive Engineering，2023, 12(1), 34-42
Publication details
Journal
Journal of Adaptive Data and Algorithmic Intelligence
Volume
1 (2026)
Issue
1 · Forthcoming issue
Article number
jadai20260012
License
CC BY 4.0