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

arXiv: https://arxiv.org/abs/2604.02721 · HTML: https://mlsanity.com/paper/2604.02721/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 27 of 27)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026)
- [TTRL: Test-Time Reinforcement Learning](https://mlsanity.com/paper/2504.16084/) (2025)
- [MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent](https://mlsanity.com/paper/2507.02259/) (2025)
- [TACO: Topics in Algorithmic COde generation dataset](https://mlsanity.com/paper/2312.14852/) (2023)
- [Competitive Programming with Large Reasoning Models](https://mlsanity.com/paper/2502.06807/) (2025)
- [CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings](https://mlsanity.com/paper/2501.01257/) (2025)
- [Learning to Discover at Test Time](https://mlsanity.com/paper/2601.16175/) (2026)
- [Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents](https://mlsanity.com/paper/2601.01885/) (2026)
- [CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning](https://mlsanity.com/paper/2507.14111/) (2025)
- [rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset](https://mlsanity.com/paper/2505.21297/) (2025)
- [Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning](https://mlsanity.com/paper/2504.05108/) (2025)
- [CodeContests+: High-Quality Test Case Generation for Competitive Programming](https://mlsanity.com/paper/2506.05817/) (2025)
- [PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation](https://mlsanity.com/paper/2509.19128/) (2025)
- [Composer 2 Technical Report](https://mlsanity.com/paper/2603.24477/) (2026)
- [ProBench: Benchmarking Large Language Models in Competitive Programming](https://mlsanity.com/paper/2502.20868/) (2025)
- [Agent Skill Acquisition for Large Language Models via CycleQD](https://mlsanity.com/paper/2410.14735/) (2024)
- [AetherCode: Evaluating LLMs' Ability to Win In Premier Programming Competitions](https://mlsanity.com/paper/2508.16402/) (2025)
- [DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism](https://mlsanity.com/paper/2510.10620/) (2025)
- [Scaling Agentic Verifier for Competitive Coding](https://mlsanity.com/paper/2602.04254/) (2026)
- [Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?](https://mlsanity.com/paper/2506.12713/) (2025)
- [When Elo Lies: Hidden Biases in Codeforces-Based Evaluation of Large Language Models](https://mlsanity.com/paper/2602.05891/) (2026)

## Built on by (most cited first, 4 of 4)

- [CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming](https://mlsanity.com/paper/2605.24693/) (2026)
- [Learning CLI Agents with Structured Action Credit under Selective Observation](https://mlsanity.com/paper/2605.08013/) (2026)
- [Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Science](https://mlsanity.com/paper/2609.15983/) (2026)
- [Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF](https://mlsanity.com/paper/2606.27580/) (2026)

## Abstract (arXiv)

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.