Abstract
Large language models for code generation often fail on execution, multilingual coverage, and contamination control, especially under frozen backbone constraints. We present CodeForge-MA, a unified framework that improves code synthesis through a multi-agent data forge, execution verified reinforced instruction tuning, and a language conditioned mixture of LoRA adapters. Four specialized agents, Composer, Reviewer, Executor, and Curator, iteratively refine instruction code pairs, validate them with tests, and filter duplicates and benchmark leakage. During training, we combine masked supervised fine tuning with a test driven reinforcement objective to align generations with executable correctness. For the larger model, we use sparse expert routing over low rank adapters to improve cross language transfer while keeping the base model unchanged at inference. Experiments show that joint data, objective, and adapter design yields robust gains across programming languages.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Gu, Z., Wu, X., Gu, S., Zhang, T., & Tong, K. (2026). CodeForge-MA: Execution-Verified Multi-Agent Learning with Language-Conditioned LoRA for Multilingual Code Generation. https://omanscience.com/en/articles/codeforge-ma-execution-verified-multi-agent-learning-with-language-conditioned-lora-for-multilingual-code-generation
MLA 9
Gu, Zhizhou, et al. "CodeForge-MA: Execution-Verified Multi-Agent Learning with Language-Conditioned LoRA for Multilingual Code Generation." https://omanscience.com/en/articles/codeforge-ma-execution-verified-multi-agent-learning-with-language-conditioned-lora-for-multilingual-code-generation.
Chicago (author–date)
Gu, Zhizhou, Xianting Wu, Siyu Gu, Tian Zhang, and Kejian Tong. 2026. "CodeForge-MA: Execution-Verified Multi-Agent Learning with Language-Conditioned LoRA for Multilingual Code Generation." https://omanscience.com/en/articles/codeforge-ma-execution-verified-multi-agent-learning-with-language-conditioned-lora-for-multilingual-code-generation.
Harvard
Gu, Z., Wu, X., Gu, S., Zhang, T. and Tong, K. (2026) 'CodeForge-MA: Execution-Verified Multi-Agent Learning with Language-Conditioned LoRA for Multilingual Code Generation', Available at: https://omanscience.com/en/articles/codeforge-ma-execution-verified-multi-agent-learning-with-language-conditioned-lora-for-multilingual-code-generation.
Vancouver
Gu Z, Wu X, Gu S, Zhang T, Tong K. CodeForge-MA: Execution-Verified Multi-Agent Learning with Language-Conditioned LoRA for Multilingual Code Generation. https://omanscience.com/en/articles/codeforge-ma-execution-verified-multi-agent-learning-with-language-conditioned-lora-for-multilingual-code-generation
IEEE
Z. Gu, X. Wu, S. Gu, T. Zhang, and K. Tong, "CodeForge-MA: Execution-Verified Multi-Agent Learning with Language-Conditioned LoRA for Multilingual Code Generation," https://omanscience.com/en/articles/codeforge-ma-execution-verified-multi-agent-learning-with-language-conditioned-lora-for-multilingual-code-generation.