AutoCode: LLMs as Problem Setters for Competitive Programming
Abstract
Writing competitive programming problems is exacting. Authors must: set constraints, input distributions, and edge cases that rule out shortcuts; target specific algorithms (e.g., max-flow, dynamic programming, data structures); and calibrate complexity beyond the reach of most competitors. We argue that this makes for an ideal test of general large language model capabilities and study whether they can do this reliably. We introduce AutoCode, which uses multiple rounds of validation to yield competition-grade problem statements and test cases. On held-out problems, AutoCode test suites approach 99% consistency with official judgments, a significant improvement over current state-of-the-art methods like HardTests, which achieve less than 81%. Furthermore, starting with a random seed problem, AutoCode can create novel variants with reference and brute-force solutions. By cross-verifying these generated solutions against test cases, we can further filter out malformed problems. Our system ensures high correctness, as verified by human experts. AutoCode successfully produces novel problems judged by Grandmaster-level (top 0.3%) competitive programmers to be of contest quality.
Cite
Text
Zhou et al. "AutoCode: LLMs as Problem Setters for Competitive Programming." International Conference on Learning Representations, 2026.Markdown
[Zhou et al. "AutoCode: LLMs as Problem Setters for Competitive Programming." International Conference on Learning Representations, 2026.](https://mlanthology.org/iclr/2026/zhou2026iclr-autocode/)BibTeX
@inproceedings{zhou2026iclr-autocode,
title = {{AutoCode: LLMs as Problem Setters for Competitive Programming}},
author = {Zhou, Shang and Zheng, Zihan and Liu, Kaiyuan and Shen, Zeyu and Cheng, Zerui and Chen, Zexing and He, Hansen and Yao, Jianzhu and Mao, Huanzhi and Mang, Qiuyang and Fu, Tianfu and Li, Beichen and Li, Dongruixuan and Chai, Wenhao and Liu, Zhuang and Korolova, Aleksandra and Henderson, Peter and Jaques, Natasha and Viswanath, Pramod and Xie, Saining and Shang, Jingbo},
booktitle = {International Conference on Learning Representations},
year = {2026},
url = {https://mlanthology.org/iclr/2026/zhou2026iclr-autocode/}
}