# GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

DevFeed: [GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning](<https://devfeed.tech/articles/grandcode-achieving-grandmaster-level-in-competitive-programming-via-agentic-reinforcement-learning-131899.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2604.02721>)

Author: Ornith Team, Xiaoya Li, Guoyin Wang, Songqiao Su, Jiwei Li, Chris Shum

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [competitive-programming](<https://devfeed.tech/topics/competitive-programming.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [grpo](<https://devfeed.tech/topics/grpo.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [competitive-programming](<https://devfeed.tech/tags/competitive-programming.md>), [contests](<https://devfeed.tech/tags/contests.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>)

## AI overview

GrandCode combines multiple agent modules--including hypothesis proposal, solving, test generation, and summarization--and improves them through post-training and online test-time reinforcement learning. Its Agentic GRPO method is designed for multi-stage rollouts with delayed rewards and substantial off-policy drift. The abstract reports that GrandCode placed first in three consecutive live Codeforces contests (Rounds 1087-1089, March 21-29, 2026), beating all human participants, including grandmasters. These results are reported in the supplied abstract; no further evaluation details are provided.

## Source excerpt

arXiv:2604.02721v4 Announce Type: replace Abstract: 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.