AI首次在编程竞赛中连续击败人类高手，达到大师级水平。
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
- 多智能体强化学习协同优化解题、测试生成等模块。
- 在三次真实比赛中均获第一，超越所有人类选手。
- 适合对AI编程能力、强化学习应用感兴趣的读者。
编程竞赛仍是人类在编码领域最后的强项之一。目前最强的AI系统仍不及顶尖人类表现：谷歌最新成果Gemini~3 Deep Think即便未在实时比赛条件下评估，也仅取得第8名。本文提出GrandCode，一种专为编程竞赛设计的多智能体强化学习系统。其突破源于两大关键：（1）协调多种智能体模块（如假设生成、求解器、测试用例生成、摘要等），通过后训练与在线测试时强化学习联合优化；（2）提出专为多阶段智能体推演设计的Agentic GRPO算法，有效应对延迟奖励与严重偏离策略的问题。GrandCode是首个在真实编程竞赛中持续战胜所有人类选手的AI系统：在最近三场Codeforces直播赛——第1087场（2026年3月21日）、第1088场（3月28日）和第1089场（3月29日）中，均排名第一，击败包括传奇大师在内的所有参赛者。该结果表明，AI已超越最强大的人类程序员，在最激烈的编码任务中占据优势。
原文摘要 · Abstract (English)
Competitive programming remains one of the last few human strongholds in coding against AI. The best AI system to date still underperforms the best humans competitive programming: the most recent best result, Google's Gemini~3 Deep Think, attained 8th place even not being evaluated under live competition conditions. In this work, we introduce GrandCode, a multi-agent RL system designed for competitive programming. The capability of GrandCode is attributed to two key factors: (1) It orchestrates a variety of agentic modules (hypothesis proposal, solver, test generator, summarization, etc) and jointly improves them through post-training and online test-time RL; (2) We introduce Agentic GRPO specifically designed for multi-stage agent rollouts with delayed rewards and the severe off-policy drift that is prevalent in agentic RL. GrandCode is the first AI system that consistently beats all human participants in live contests of competitive programming: in the most recent three Codeforces live competitions, i.e., Round~1087 (Mar 21, 2026), Round~1088 (Mar 28, 2026), and Round~1089 (Mar 29, 2026), GrandCode placed first in all of them, beating all human participants, including legendary grandmasters. GrandCode shows that AI systems have reached a point where they surpass the strongest human programmers on the most competitive coding tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。