Abstract
Programming is a powerful and ubiquitous problem-solving tool. Systems that can assist programmers or even generate programs themselves could make programming more productive and accessible. Recent transformer-based neural network models show impressive code generation abilities yet still perform poorly on more complex tasks requiring problem-solving skills, such as competitive programming problems. Here, we introduce AlphaCode, a system for code generation that achieved an average ranking in the top 54.3% in simulated evaluations on recent programming competitions on the Codeforces platform. AlphaCode solves problems by generating millions of diverse programs using specially trained transformer-based networks and then filtering and clustering those programs to a maximum of just 10 submissions. This result marks the first time an artificial intelligence system has performed competitively in programming competitions.
Publisher
American Association for the Advancement of Science (AAAS)
Reference84 articles.
1. Toward automatic program synthesis
2. Application of recursive arithmetic to the problem of circuit synthesis.;Church A.;J. Symb. Log.,1963
3. C. C. Green “Application of theorem proving to problem solving” in Readings in Artificial Intelligence B. L. Webber N. J. Nilsson Eds. (Elsevier 1981) pp. 202–222.
4. The rust language
5. Scratch
Cited by
271 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. CoSec: On-the-Fly Security Hardening of Code LLMs via Supervised Co-decoding;Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis;2024-09-11
2. FDI: Attack Neural Code Generation Systems through User Feedback Channel;Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis;2024-09-11
3. The promise and challenges of generative AI in education;Behaviour & Information Technology;2024-09-02
4. The “Code” of Ethics: A Holistic Audit of AI Code Generators;IEEE Transactions on Dependable and Secure Computing;2024-09
5. MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning;Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining;2024-08-24