paper-with-me

Papers

Competitive Programming with Large Reasoning Models

2025-02-03 · OpenAI, :, Ahmed El-Kishky, Alexander Wei, Andre Saraiva, Borys Minaev, Daniel Selsam, David Dohan, Francis Song, Hunter Lightman, Ignasi Clavera, Jakub Pachocki, Jerry Tworek, Lorenz Kuhn, Lukasz Kaiser, Mark Chen, Max Schwarzer, Mostafa Rohaninejad, Nat McAleese, o3 contributors, Oleg Mürk, Rhythm Garg, Rui Shu, Szymon Sidor, Vineet Kosaraju, Wenda Zhou

We show that reinforcement learning applied to large language models (LLMs) significantly boosts performance on complex coding and reasoning tasks. Additionally, we compare two general-purpose reasoning models - OpenAI o1 and an early checkpoint of o3 - with a domain-specific system, o1-ioi, which uses hand-engineered inference strategies designed for competing in the 2024 International Olympiad in Informatics (IOI). We competed live at IOI 2024 with o1-ioi and, using hand-crafted test-time strategies, placed in the 49th percentile. Under relaxed competition constraints, o1-ioi achieved a gold medal. However, when evaluating later models such as o3, we find that o3 achieves gold without hand-crafted domain-specific strategies or relaxed constraints. Our findings show that although specialized pipelines such as o1-ioi yield solid improvements, the scaled-up, general-purpose o3 model surpasses those results without relying on hand-crafted inference heuristics. Notably, o3 achieves a gold medal at the 2024 IOI and obtains a Codeforces rating on par with elite human competitors. Overall, these results indicate that scaling general-purpose reinforcement learning, rather than relying on domain-specific techniques, offers a robust path toward state-of-the-art AI in reasoning domains, such as competitive programming.

📄 PDF Abstract BibTeX arXiv:2502.06807

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

ProBench: Benchmarking Large Language Models in Competitive Programming

2025-02-28 · Lei Yang, Renren Jin, Ling Shi, Jianxiang Peng 외

With reasoning language models such as OpenAI-o3 and DeepSeek-R1 emerging, large language models (LLMs) have entered a new phase of development. However, existing benchmarks for coding evaluation are gradually inadequate…

AttributeBenchmarkingFairness

Idea First, Code Later: Disentangling Problem Solving from Code Generation in Evaluating LLMs for Competitive Programming

2026-01-16 · Sama Hadhoud, Alaa Elsetohy, Frederikus Hudi, Jan Christian Blaise Cruz 외 arxiv

Large Language Models (LLMs) increasingly succeed on competitive programming problems, yet existing evaluations conflate algorithmic reasoning with code-level implementation. We argue that competitive programming is fund…

Code Generation

CodeContests+: High-Quality Test Case Generation for Competitive Programming

2025-06-06 · Zihan Wang, Siyao Liu, Yang Sun, Hongyan Li 외

Competitive programming, due to its high reasoning difficulty and precise correctness feedback, has become a key task for both training and evaluating the reasoning capabilities of large language models (LLMs). However, …

Reinforcement Learning (RL)

DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation

2025-11-09 · Speed Zhu, Jianwei Cai, Guang Chen, Lulu Wu 외 arxiv

Recent reasoning-first models (e.g., OpenAI o1, DeepSeek R1) have spurred a resurgence of interest in RLVR. Nevertheless, advances are dominated by mathematics (e.g., AIME), with competitive-programming code generation u…

Reinforcement LearningCode Generation

OJBench: A Competition Level Code Benchmark For Large Language Models

2025-06-19 · Zhexu Wang, Yiping Liu, Yejie Wang, Wenyang He 외

Recent advancements in large language models (LLMs) have demonstrated significant progress in math and code reasoning capabilities. However, existing code benchmark are limited in their ability to evaluate the full spect…

Math