arXiv (Cornell University)
ACECode: A Reinforcement Learning Framework for Aligning Code Efficiency and Correctness in Code Language Models
December 2024 • Chengran Yang, Hong Jin Kang, Jieke Shi, David Lo
CodeLLMs have demonstrated remarkable advancements in software engineering tasks. However, while these models can generate functionally correct code, they often produce code that is inefficient in terms of runtime. This inefficiency is particularly problematic in resource-constrained environments, impacting software performance and sustainability. Existing approaches for optimizing code efficiency for CodeLLMs like SOAP and PIE exhibit certain limitations. SOAP requires a compatible execution environment and prede…