{"ID":2878962,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.20124","arxiv_id":"2508.20124","title":"Towards Better Correctness and Efficiency in Code Generation","abstract":"While code large language models have demonstrated remarkable progress in code generation, the generated code often exhibits poor runtime efficiency, limiting its practical application in performance-sensitive scenarios. To address this limitation, we propose an efficiency-oriented reinforcement learning framework guided by a novel performance reward. Based on this framework, we take a deeper dive into the code efficiency problem, identifying then proposing methods to overcome key bottlenecks: (1) Dynamic exploration overcomes the static data constraints of offline fine-tuning, enabling the discovery of more efficient code implementations. (2) The error-insensitive reinforcement learning method and high-contrast efficiency signals are crucial for mitigating systematic errors and achieving effective optimization. (3) Online exploration is most effective when starting from a high-correctness baseline, as this allows for efficiency improvements without sacrificing accuracy. With these discoveries, we finally propose a two-stage tuning method, which achieves high and balanced performance across correctness and efficiency. The results of experiments show the effectiveness of the method, which improves code correctness by 10.18\\% and runtime efficiency by 7.75\\% on a 7B model, achieving performance comparable to much larger model.","short_abstract":"While code large language models have demonstrated remarkable progress in code generation, the generated code often exhibits poor runtime efficiency, limiting its practical application in performance-sensitive scenarios. To address this limitation, we propose an efficiency-oriented reinforcement learning framework guid...","url_abs":"https://arxiv.org/abs/2508.20124","url_pdf":"https://arxiv.org/pdf/2508.20124v1","authors":"[\"Yunlong Feng\",\"Yang Xu\",\"Xiao Xu\",\"Binyuan Hui\",\"Junyang Lin\"]","published":"2025-08-24T16:47:19Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Language Model\",\"LoRA\"]","has_code":false}