AI Paper Atlas

Research map / Large language models / Agents, code and math

AutoCode: LLMs as Problem Setters for Competitive Programming

Shang Zhou, Zihan Zheng, Kaiyuan Liu, Zeyu Shen, Zerui Cheng, Zexing Chen, Hansen He, Jianzhu Yao, Huanzhi Mao, Qiuyang Mang, Tianfu Fu, Beichen Li and 9 more

ICLR 2026 · Large language models › Agents, code and math · approach: Execution-based code verification · 13 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add prompt optimization (ablation)AutoCode · 720 Codeforces problemsFNR (%): 2.9 -> 1.2Improved
add exhaustive small-data generator strategy (ablation)AutoCode · 720 Codeforces problemsFPR (%): 1.7 -> 1.3Improved
add random/extreme generator strategy (ablation)AutoCode · 720 Codeforces problemsFPR (%): 1.6 -> 1.3Improved
add TLE-inducing generator strategy (ablation)AutoCode · 720 Codeforces problemsconsistency (%): 98.6 -> 98.7No clear effect
use AutoCode test generation instead of HardTests teststest suites · 7538-problem benchmarkconsistency (%): 81.0 -> 91.1Improved
filter generated problems with brute-force dual verification (ablation)problem generation · generated problemsreference correctness (%): 86 -> 94Improved
use LLM (o3) judgments instead of human experts for problem qualityproblem quality assessment · generated problemscorrelation: 0.07 (quality), 0.11 (novelty)Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy