mlsanityData to 14 Oct 2026

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

arXiv 2604.02721 ↗First posted 3 Apr 2026cs.AIcited by 4

On the map: LLM agents and tool use → Software engineering coding agents

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.

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.

Builds on

27 of 40 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026Composer 2 Technical Report25 Mar
  2. 2026Scaling Agentic Verifier for Competitive Coding4 Feb

Other references · 25

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2024Qwen2.5 Technical Reportcited by 4,942
  5. 2024GPT-4o System Cardcited by 4,588
  6. 2022Competition-Level Code Generation with AlphaCodecited by 1,462
  7. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 278
  8. 2025TTRL: Test-Time Reinforcement Learningcited by 275
  9. 2025MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agentcited by 246
  10. 2023TACO: Topics in Algorithmic COde generation datasetcited by 160
  11. 2025Competitive Programming with Large Reasoning Modelscited by 119
  12. 2025CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratingscited by 115
13 more
  1. 2026Learning to Discover at Test Timecited by 115
  2. 2026Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agentscited by 78
  3. 2025CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learningcited by 61
  4. 2025rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Datasetcited by 51
  5. 2025Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learningcited by 46
  6. 2025CodeContests+: High-Quality Test Case Generation for Competitive Programmingcited by 46
  7. 2025PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generationcited by 32
  8. 2025ProBench: Benchmarking Large Language Models in Competitive Programmingcited by 15
  9. 2024Agent Skill Acquisition for Large Language Models via CycleQDcited by 12
  10. 2025AetherCode: Evaluating LLMs' Ability to Win In Premier Programming Competitionscited by 11
  11. 2025DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelismcited by 7
  12. 2025Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?cited by 6
  13. 2026When Elo Lies: Hidden Biases in Codeforces-Based Evaluation of Large Language Modelscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programmingcited by 3
  2. 2026Learning CLI Agents with Structured Action Credit under Selective Observationcited by 1
  3. 2026Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Sciencecited by 1
  4. 2026Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHFcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Cross-Benchmark Transfer from RL on Agentic Coding Tasks
  2. 2026Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution
  3. 2026Post-Training Language Models for Gold-Medal Performance in Coding Competitions
  4. 2026X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests
  5. 2026CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
  6. 2024FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning
  7. 2026MARS: Multi-Specialist LLM Relay System for Competitive Programming
  8. 2026CODE-SHARP: Continuous Open-ended Discovery and Evolution of Skills as Hierarchical Reward Programs