GrandCode: 通过代理强化学习实现竞技编程的Grandmaster级别
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
AI总结：
本文提出GrandCode，一种用于竞技编程的多代理强化学习系统，通过代理模块协同训练和代理GRPO算法，实现了在竞技编程比赛中超越人类选手的突破。
摘要：
竞技编程仍然是人类在编码对抗AI方面的最后几个强项之一。目前最好的AI系统仍无法超越顶尖的人类竞技编程者：最近的最佳结果，谷歌的Gemini~3 Deep Think，在未经过现场竞赛条件评估的情况下仅获得第八名。在本工作中，我们介绍了GrandCode，一种为竞技编程设计的多代理强化学习系统。GrandCode的能力归因于两个关键因素：(1) 它协调了多种代理模块（假设提案、求解器、测试生成器、总结等）并通过后训练和在线测试时间强化学习共同改进它们；(2) 我们引入了专门设计用于多阶段代理回放的代理GRPO，以应对延迟奖励和严重的非策略漂移问题，这在代理强化学习中很常见。GrandCode是首个在竞技编程现场比赛中持续击败所有人类参与者的AI系统：在最近的三次Codeforces现场比赛中，即Round~1087（2026年3月21日）、Round~1088（2026年3月28日）和Round~1089（2026年3月29日），GrandCode在所有比赛中均取得第一，击败了所有人类参与者，包括传奇的Grandmaster级选手。GrandCode表明，AI系统已经达到了在最具有挑战性的编码任务上超越最强人类程序员的水平。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
