Competitive Programming with Large Reasoning Models
OpenAI
OpenAI, :, Ahmed El-Kishky, Alexander Wei, Andre Saraiva, Borys Minaiev, Daniel Selsam, David Dohan, Francis Song, Hunter Lightman, Ignasi Clavera, Jakub Pachoc… 展开作者
OpenAI, :, Ahmed El-Kishky, Alexander Wei, Andre Saraiva, Borys Minaiev, 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.
Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming
Carnegie Mellon University(卡内基梅隆大学);University of Pennsylvania(宾夕法尼亚大学);Mohamed Bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Petuum Inc.(Petuum公司)
ELABORATION: A Comprehensive Benchmark on Human-LLM Competitive Programming
Sichuan University(四川大学);Tianjin University of Science and Technology(天津科技大学);Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, China(机器学习与工业智能工程研究中心,教育部,中国);Vanderbilt University(范德比大学)
InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information
School of Cyber Science and Engineering, Huazhong University of Science and Technology(华中科技大学网络空间科学与工程学院);Key Laboratory of Cyberspace Security, Ministry of Education(教育部网络空间安全重点实验室);Hubei Key Laboratory of Distributed System Security(湖北省分布式系统安全重点实验室)
LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?
New York University(纽约大学);Princeton University(普林斯顿大学);University of California San Diego(加利福尼亚大学圣地亚哥分校);University of Washington(华盛顿大学);Canyon Crest Academy(峡谷克雷斯特学院);University of Waterloo(滑铁卢大学);McGill University(麦吉尔大学)
AutoCode: LLMs as Problem Setters for Competitive Programming
University of California San Diego(加州大学圣地亚哥分校);New York University(纽约大学);University of Washington(华盛顿大学);Princeton University(普林斯顿大学);University of California Berkeley(加州大学伯克利分校);OpenAI;Massachusetts Institute of Technology(麻省理工学院);University of Waterloo(滑铁卢大学);Sentient Labs
MultiLingPoT: Enhancing Mathematical Reasoning with Multilingual Program Fine-tuning
Fudan University(复旦大学);MYbank, Ant Group(蚂蚁集团MYbank);School of Computer Science, Fudan University(复旦大学计算机学院);School of Data Science, Fudan University(复旦大学数据科学学院)
SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving
The University of Hong Kong(香港大学);University of California Los Angeles(加州大学洛杉矶分校);Tsinghua University(清华大学);University of Michigan Ann Arbor(密歇根大学安娜堡分校);The Ohio State University(俄亥俄州立大学);University of Edinburgh(爱丁堡大学);The Chinese University of Hong Kong(香港中文大学);The Hong Kong Polytechnic University(香港理工大学);Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));LMSYS Org(LMSYS组织)
OJBench: A Competition Level Code Benchmark For Large Language Models
Beijing University of Posts and Telecommunications(北京邮电大学);Tsinghua University(清华大学);University of Chinese Academy of Sciences(中国科学院大学);Peking University(北京大学);Moonshot AI
Are Language Models Efficient Reasoners? A Perspective from Logic Programming
ETH Zürich(苏黎世联邦理工学院);MPI for Intelligent Systems, Tübingen(智能系统马克斯·普朗克研究所);EPFL(苏黎世联邦理工学院);Idiap Research Institute(Idiap研究机构);Purdue University(普渡大学)
Post-Proceedings of the First International Workshop on Learning and Nonmonotonic Reasoning
知识表示与推理和机器学习是人工智能的两个重要领域。非单调逻辑程序设计(NMLP)和回答集程序设计(ASP)为常识知识的表示和推理提供了形式语言,实现了人工智能中的声明式问题求解。另一方面,归纳逻辑程序设计(ILP)在逻辑程序设计中实现了机器学习,为归纳学习提供了形式化的背景,并将其应用于关系学习和数据采掘等领域。一般来说,NMLP和ASP实现了非单调推理,但缺乏学习能力。相反,ILP实现了归纳学习,而大多数技术都是在经典单调逻辑下发展起来的。在这种背景下,一些研究者试图将各种技术结合到非单调ILP中。这样的组合将引入一个学习机制的程序,并将利用新的应用程序的NMLP侧,而在ILP侧,它将扩展的表示语言,使我们能够使用现有的求解器。学习和非单调推理之间的交叉也可以发生在诸如使用答案集求解器用于ILP、在运行答案集求解器时加速学习、学习动作理论、学习动力系统中的转换规则、溯因学习、学习具有抑制的生物网络以及涉及默认和否定的应用中。该研讨会是首次尝试提供一个公开论坛,以确定问题和讨论具有互补专长的研究人员之间可能的合作。该研讨会于2013年9月15日在西班牙Corunna举行。这篇论文集包含五篇技术论文(六篇被接受的论文中的五篇)和Luc De Raedt邀请演讲的摘要。
COBRA-PPM: A Causal Bayesian Reasoning Architecture Using Probabilistic Programming for Robot Manipulation Under Uncertainty
Oxford Robotics Institute, Dept. Engineering Science, University of Oxford, UK(牛津大学机器人研究所);Microsoft Research, Redmond, WA, USA(微软研究院);Bristol Robotics Laboratory, School of Engineering, University of the West of England, Bristol, UK(布里斯托尔机器人实验室)