GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
cs.AI
Submitted: 2026-04-03
Updated: 2026-11-11
Code: https://github.com/thinking-machines-lab/tinker
Terminology
Sources
- TTRL: Test-Time Reinforcement Learning
- Composer 2 Technical Report
- DeepSeek-V3 Technical Report
- Competitive Programming with Large Reasoning Models
- Agent Skill Acquisition for Large Language Models via CycleQD
- TACO: Topics in Algorithmic COde generation dataset
- Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?
- CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
- rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset
- The Llama 3 Herd of Models
- Scaling Agentic Verifier for Competitive Coding
- GPT-4 Technical Report
- GPT-4o System Card
- OpenAI o1 System Card
- PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation
- CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning
- AetherCode: Evaluating LLMs' Ability to Win In Premier Programming Competitions
- CodeContests+: High-Quality Test Case Generation for Competitive Programming
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents