Fetching the paper…

Reading the bibliography…

2025

Towards Better Correctness and Efficiency in Code Generation

Feng, Yunlong, Xu, Yang, Xu, Xiao et al.

Original
PDF
Post on X

Understand

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.

Towards Better Correctness and Efficiency in Code Generation · Around

Built on

Applied Linear Statistical Models (5th ed.)
Enter, H. F. S. 2008 · 2008
Earlier work this paper cites.
Language Models are Few-Shot Learners
Brown, T. B.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A.; Agarwal, S.; Herbert-Voss, A.; Krueger, G.; Henighan, T.; Child, R.; Ramesh, A.; Ziegler, D. M.; Wu, J.; Winter, C.; Hesse, C.; Chen, M.; Sigler, E.; Litwin, M.; Gray, S.; Chess, B.; Clark, J.; Berner, C.; McCandlish, S.; Radford, A.; Sutskever, I.; and Amodei, D. 2020 · 2020
Earlier work this paper cites.
Competition-level code generation with alphacode
Li, Y.; Choi, D.; Chung, J.; Kushman, N.; Schrittwieser, J.; Leblond, R.; Eccles, T.; Keeling, J.; Gimeno, F.; Dal Lago, A.; et al. 2022 · 2022
Earlier work this paper cites.
Gpt-4 technical report
Original
Achiam, J.; Adler, S.; Agarwal, S.; Ahmad, L.; Akkaya, I.; Aleman, F. L.; Almeida, D.; Altenschmidt, J.; Altman, S.; Anadkat, S.; et al. 2023 · 2023
Earlier work this paper cites.
Qwen technical report
Original
Bai, J.; Bai, S.; Chu, Y.; Cui, Z.; Dang, K.; Deng, X.; Fan, Y.; Ge, W.; Han, Y.; Huang, F.; et al. 2023 · 2023
Earlier work this paper cites.
Mistral 7B (2023)
Original
Jiang, A.; Sablayrolles, A.; Mensch, A.; Bamford, C.; Chaplot, D.; de las Casas, D.; Bressand, F.; Lengyel, G.; Lample, G.; Saulnier, L.; et al. 2023 · 2023
Earlier work this paper cites.
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Rafailov, R.; Sharma, A.; Mitchell, E.; Manning, C. D.; Ermon, S.; and Finn, C. 2023 · 2023
Earlier work this paper cites.
Llama 2: Open foundation and fine-tuned chat models
Original
Touvron, H.; Martin, L.; Stone, K.; Albert, P.; Almahairi, A.; Babaei, Y.; Bashlykov, N.; Batra, S.; Bhargava, P.; Bhosale, S.; et al. 2023 · 2023
Earlier work this paper cites.
CodeT5+: Open Code Large Language Models for Code Understanding and Generation
Wang, Y.; Le, H.; Gotmare, A.; Bui, N.; Li, J.; and Hoi, S. 2023 · 2023
Earlier work this paper cites.

Similar

Magicoder: Source code is all you need
Original
Wei, Y.; Wang, Z.; Liu, J.; Ding, Y.; and Zhang, L. 2023 · 2023
Cited alongside, same era.
Wavecoder: Widespread and versatile enhanced instruction tuning with refined data generation
Original
Yu, Z.; Zhang, X.; Shang, N.; Huang, Y.; Xu, C.; Zhao, Y.; Hu, W.; and Yin, Q. 2023 · 2023
Cited alongside, same era.
Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs
Ahmadian, A.; Cremer, C.; Gallé, M.; Fadaee, M.; Kreutzer, J.; Pietquin, O.; Üstün, A.; and Hooker, S. 2024 · 2024
Cited alongside, same era.
Claude 3.5 Sonnet
Anthropic. 2024 · 2024
Cited alongside, same era.
Mercury: A Code Efficiency Benchmark for Code Large Language Models
Du, M.; Luu, A. T.; Ji, B.; Liu, Q.; and Ng, S. 2024 · 2024
Cited alongside, same era.

Then

Starcoder 2 and the stack v2: The next generation
Original
Lozhkov, A.; Li, R.; Allal, L. B.; Cassano, F.; Lamy-Poirier, J.; Tazi, N.; Tang, A.; Pykhtar, D.; Liu, J.; Wei, Y.; et al. 2024 · 2024
Later among the works it cites.
WizardCoder: Empowering Code Large Language Models with Evol-Instruct
Luo, Z.; Xu, C.; Zhao, P.; Sun, Q.; Geng, X.; Hu, W.; Tao, C.; Ma, J.; Lin, Q.; and Jiang, D. 2024 · 2024
Later among the works it cites.
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Original
Shao, Z.; Wang, P.; Zhu, Q.; Xu, R.; Song, J.; Bi, X.; Zhang, H.; Zhang, M.; Li, Y. K.; Wu, Y.; and Guo, D. 2024 · 2024
Later among the works it cites.
HybridFlow: A Flexible and Efficient RLHF Framework
Sheng, G.; Zhang, C.; Ye, Z.; Wu, X.; Zhang, W.; Zhang, R.; Peng, Y.; Lin, H.; and Wu, C. 2024 · 2024
Later among the works it cites.
Learning Performance-Improving Code Edits
Shypula, A.; Madaan, A.; Zeng, Y.; Alon, U.; Gardner, J. R.; Yang, Y.; Hashemi, M.; Neubig, G.; Ranganathan, P.; Bastani, O.; and Yazdanbakhsh, A. 2024 · 2024

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

The llama 3 herd of models

Dubey, A.; Jauhri, A.; Pandey, A.; Kadian, A.; Al-Dahle, A.; Letman, A.; Mathur, A.; Schelten, A.; Yang, A.; Fan, A.; et al. 2024 · 2024

Cited alongside, same era.

EffiBench: Benchmarking the Efficiency of Automatically Generated Code

Huang, D.; Qing, Y.; Shang, W.; Cui, H.; and Zhang, J. 2024b · 2024

Cited alongside, same era.

Qwen2. 5-Coder Technical Report

Original

Hui, B.; Yang, J.; Cui, Z.; Yang, J.; Liu, D.; Zhang, L.; Liu, T.; Zhang, J.; Yu, B.; Dang, K.; et al. 2024 · 2024

Cited alongside, same era.

Evaluating Language Models for Efficient Code Generation

Liu, J.; Xie, S.; Wang, J.; Wei, Y.; Ding, Y.; and Zhang, L. 2024 · 2024

Cited alongside, same era.

SOAP: Enhancing Efficiency of Generated Code via Self-Optimization

Huang, D.; Dai, J.; Weng, H.; Wu, P.; Qing, Y.; Zhang, J. M.; Cui, H.; and Guo, Z. 2024a

Cited in the paper.

Effi-Code: Unleashing Code Efficiency in Language Models

Huang, D.; Zeng, G.; Dai, J.; Luo, M.; Weng, H.; Qing, Y.; Cui, H.; Guo, Z.; and Zhang, J. M. 2024c

Cited in the paper.

Qwen2 Technical Report

Yang, A.; Yang, B.; Hui, B.; Zheng, B.; Yu, B.; Zhou, C.; Li, C.; Li, C.; Liu, D.; Huang, F.; Dong, G.; Wei, H.; Lin, H.; Tang, J.; Wang, J.; Yang, J.; Tu, J.; Zhang, J.; Ma, J.; Xu, J.; Zhou, J.; Bai, J.; He, J.; Lin, J.; Dang, K.; Lu, K.; Chen, K.; Yang, K.; Li, M.; Xue, M.; Ni, N.; Zhang, P.; Wang, P.; Peng, R.; Men, R.; Gao, R.; Lin, R.; Wang, S.; Bai, S.; Tan, S.; Zhu, T.; Li, T.; Liu, T.; Ge, W.; Deng, X.; Zhou, X.; Ren, X.; Zhang, X.; Wei, X.; Ren, X.; Fan, Y.; Yao, Y.; Zhang, Y.; Wan, Y.; Chu, Y.; Liu, Y.; Cui, Z.; Zhang, Z.; and Fan, Z. 2024a

Cited in the paper.

Later among the works it cites.

ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?

Waghjale, S.; Veerendranath, V.; Wang, Z. Z.; and Fried, D. 2024 · 2024

Later among the works it cites.

LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Zheng, Y.; Zhang, R.; Zhang, J.; Ye, Y.; Luo, Z.; Feng, Z.; and Ma, Y. 2024 · 2024

Later among the works it cites.

LLM4EFFI: Leveraging Large Language Models to Enhance Code Efficiency and Correctness

Original

Ye, T.; Huang, W.; Zhang, X.; Ma, T.; Liu, P.; Yin, J.; and Wang, W. 2025 · 2025

Closest in time.

BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation

Zhu, A.; Asawa, P.; Davis, J. Q.; Chen, L.; Hanin, B.; Stoica, I.; Gonzalez, J. E.; and Zaharia, M. 2025 · 2025

Closest in time.