Competitive Programming

Follow this topic Ask about this topic

Competitive programming asks systems to turn precise problem statements into algorithms and programs that pass hidden tests under time and resource limits. Current AI approaches include post-training with curated or synthetic tasks, reinforcement learning from execution feedback, iterative self-refinement, and multi-agent workflows; repeated independent sampling can also be effective. Benchmarks span contest archives such as Codeforces and CodeContests, Olympiad problems, and interactive tasks, while adversarial testing checks whether solutions or official test suites miss edge cases. Models can now reach elite contest performance in some settings, but reliability, interactive reasoning, test coverage, and the cost of extensive test-time computation remain central challenges.

Latest papers

17 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

How Prompt Style Affects AI Accuracy and Speed in Competitive Programming
Oct 21, 2026Saad B. Alarifi, Mohammed A. AlamLLM Prompting Prompt Sensitivity
Riyadh Schools Riyadh, Saudi Arabia · Department of Computer Science Northwestern University Evanston, IL, USA
Post-Training Language Models for Gold-Medal Performance in Coding Competitions
Sep 2, 2026Aleksander Ficek, Sean Narenthiran, Mehrzad Samadi +2Code Generation Competitive Programming
NVIDIA
InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information
Aug 30, 2026Jiaze Li, Aocheng Shen, Bing Liu +4Code Generation Benchmarks Competitive Programming
School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China · Key Laboratory of Cyberspace Security, Ministry of Education, Zhengzhou, China · Hubei Key Laboratory of Distributed System Security, Wuhan, China.
MARS: Multi-Specialist LLM Relay System for Competitive Programming
Aug 24, 2026Andrei Mikhailov, Mikhail Burtsev, Alsu SagirovaLLM-Based Program Synthesis Multi-Agent Coding
MIRAI · London Institute for Mathematical Sciences · AXXX
Coding Agents as Test-Suite Auditors: Finding What Official Suites Miss While Approaching What They Catch
Aug 3, 2026Shuyang Xie, Shuxiao Xie, Feng Zhu +2Automated Software Testing Benchmark Auditing
Harbin Institute of Technology · Fudan University · Sun Yat-sen University
Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming
Jun 11, 2026Tingqiang Xu, Hangrui Zhou, Tianle Cai +2Automated Program Repair Competitive Programming
Institute for Interdisciplinary Information Sciences, Tsinghua University · Universal Online Judge · ByteDance Seed +1
STAB: Specification-driven Testing for Algorithmic Bottlenecks
May 27, 2026Soohan Lim, Joonghyuk Hahn, Hyundong Jin +1Competitive Programming Automated Test Generation
Yonsei University, Seoul, Republic of Korea
CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming
May 23, 2026Peisong Wang, Bowen Liu, Zehua Li +4Code Generation LLM-Based Program Synthesis
The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China
Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution
May 14, 2026Han Li, Jinyu Tian, Rili Feng +10RL for Code Generation Continual Learning for LLM Agents
Nanjing University · Independent Researcher · Tsinghua University
When Independent Sampling Outperforms Agentic Reasoning
May 8, 2026Yihe Dong, Boris ShigidaCost-Aware Inference Competitive Programming
Princeton University
MAS-Algorithm: A Workflow for Solving Algorithmic Programming Problems with a Multi-Agent System
May 7, 2026Yuliang Xu, Xiang Xu, Yao Wan +2Competitive Programming Multi-Agent Coding
1Peking University · 2Alibaba Group · 3Huazhong University of Science and Technology
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
Apr 3, 2026Ornith Team, Xiaoya Li, Guoyin Wang +3RL for Code Generation Agentic RL
DeepReinforce Team
Scaling Reasoning Tokens via RL and Parallel Thinking: Evidence From Competitive Programming
Apr 1, 2026Qianfan Zhang, Tianyu Guo, Xuandi Ren +4Parallel Reasoning in Language Models Test-Time Scaling
Princeton University · UC Berkeley · Stanford University +1
RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning
Apr 1, 2026Shaopeng Fu, Xingxing Zhang, Li Dong +1RL for Code Generation LLM Self-Refinement
Work done during an internship at Microsoft Research · KAUST · Microsoft Research
CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions
Feb 23, 2026Jingwei Shi, Xinxiang Yin, Jing Huang +2Automated Test Generation Adversarial Scenario Generation
Shanghai University of Finance and Economics · Northwestern Polytechnical University · Meituan +1
X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests
Jan 11, 2026Jie Wu, Haoling Li, Xin Zhang +8RL for Code Generation Synthetic Data Generation
Tsinghua University · Microsoft
LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?
Oct 10, 2025Kaijian Zou, Aaron Xiong, Yunxiang Zhang +6LLM Evaluation Competitive Programming
University of Michigan, Ann Arbor.

Oct 21, 2026J/K move · Enter open · S save

How Prompt Style Affects AI Accuracy and Speed in Competitive Programming

Saad B. Alarifi, Mohammed A. Alam

Riyadh Schools Riyadh, Saudi Arabia · Department of Computer Science Northwestern University Evanston, IL, USA

LLM Prompting Prompt Sensitivity Language Model Generation Evaluation Competitive Programming

Open paper AskPDF arXiv

Large language models are increasingly used in competitive programming, and their outputs are sensitive to how a prompt is phrased. Prior work has compared prompt strategies for accuracy on competitive programming, but not for runtime speed, and has not situated the results against human performance. In an exploratory study of one prompt in each of nine styles on GPT-5.5 across three accuracy tasks from the International Olympiad in Informatics (IOI) and two NP-hard speed tasks, we found that no single prompt was best: the strongest prompt depended on the task type and on whether results were summarized by the mean or the median, suggesting that, at least for these tasks, prompt style should be matched to the objective rather than treated as universal. Many differences in mean scores came from a few outlier runs, showing that evaluating prompting by a single metric can obscure how much its effectiveness varies. Compared descriptively with human IOI contestants, who worked under different conditions, the AI was neither strictly better nor strictly worse, exceeding the average contestant on one task but falling short on the other two. By extending prompt comparison from accuracy to runtime speed and grounding it against human performance, this study gives a broader picture of how prompt style affects competitive programming performance.