# rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset

arXiv: https://arxiv.org/abs/2505.21297 · HTML: https://mlsanity.com/paper/2505.21297/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 15 of its 35 references that are in the map.
- First posted on arXiv 27 May 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 15 of 15)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://mlsanity.com/paper/2501.04519/) (2025)
- [TACO: Topics in Algorithmic COde generation dataset](https://mlsanity.com/paper/2312.14852/) (2023)
- [Phi-4-reasoning Technical Report](https://mlsanity.com/paper/2504.21318/) (2025)
- [OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models](https://mlsanity.com/paper/2411.04905/) (2024)
- [OpenCodeReasoning: Advancing Data Distillation for Competitive Coding](https://mlsanity.com/paper/2504.01943/) (2025)
- [ACECODER: Acing Coder RL via Automated Test-Case Synthesis](https://mlsanity.com/paper/2502.01718/) (2025)
- [Can Language Models Solve Olympiad Programming?](https://mlsanity.com/paper/2404.10952/) (2024)
- [SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM](https://mlsanity.com/paper/2504.14286/) (2025)
- [Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning](https://mlsanity.com/paper/2403.02333/) (2024)
- [Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency](https://mlsanity.com/paper/2309.17272/) (2023)

## Built on by (most cited first, 30 of 51)

- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [Embarrassingly Simple Self-Distillation Improves Code Generation](https://mlsanity.com/paper/2604.01193/) (2026)
- [LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts](https://mlsanity.com/paper/2510.19363/) (2025)
- [HardTests: Synthesizing High-Quality Test Cases for LLM Coding](https://mlsanity.com/paper/2505.24098/) (2025)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation](https://mlsanity.com/paper/2509.16198/) (2025)
- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value](https://mlsanity.com/paper/2512.14051/) (2025)
- [Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team](https://mlsanity.com/paper/2506.14234/) (2025)
- [Propose, Solve, Verify: Self-Play Through Formal Verification](https://mlsanity.com/paper/2512.18160/) (2025)
- [Learn from Your Mistakes: Self-Correcting Masked Diffusion Models](https://mlsanity.com/paper/2602.11590/) (2026)
- [Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training](https://mlsanity.com/paper/2510.20956/) (2025)
- [AutoCode: LLMs as Problem Setters for Competitive Programming](https://mlsanity.com/paper/2510.12803/) (2025)
- [Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought](https://mlsanity.com/paper/2510.04230/) (2025)
- [Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text](https://mlsanity.com/paper/2601.22975/) (2026)
- [Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning](https://mlsanity.com/paper/2508.05710/) (2025)
- [Hermes 4 Technical Report](https://mlsanity.com/paper/2508.18255/) (2025)
- [Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning](https://mlsanity.com/paper/2509.22824/) (2025)
- [LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning](https://mlsanity.com/paper/2602.01705/) (2026)
- [Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data](https://mlsanity.com/paper/2512.23422/) (2025)
- [CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models](https://mlsanity.com/paper/2602.17684/) (2026)
- [EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning](https://mlsanity.com/paper/2603.12698/) (2026)
- [Closing the Data Loop: Using OpenDataArena to Engineer Superior Training Datasets](https://mlsanity.com/paper/2601.09733/) (2025)
- [GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning](https://mlsanity.com/paper/2604.02721/) (2026)
- [InCoder-32B-Thinking: Industrial Code World Model for Thinking](https://mlsanity.com/paper/2604.03144/) (2026)
- [K2-V2: A 360-Open, Reasoning-Enhanced LLM](https://mlsanity.com/paper/2512.06201/) (2025)
- [Incentivizing In-depth Reasoning over Long Contexts with Process Advantage Shaping](https://mlsanity.com/paper/2601.12465/) (2026)
- [FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale](https://mlsanity.com/paper/2605.14445/) (2026)
- [The Valley of Code Reasoning: Scaling Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2510.06101/) (2025)
- [A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning](https://mlsanity.com/paper/2510.18814/) (2025)

## Abstract (arXiv)

Advancing code reasoning in large language models (LLMs) is fundamentally limited by the scarcity of high-difficulty datasets, especially those with verifiable input-output test cases necessary for rigorous solution validation at scale. We introduce rStar-Coder, which significantly improves LLM code reasoning capabilities by constructing a large-scale, verified dataset of 418K competition-level code problems, 580K long-reasoning solutions along with rich test cases of varying difficulty. This is achieved through three core contributions: (1) we curate competitive programming code problems and oracle solutions to synthesize new, solvable problems; (2) we introduce a reliable input-output test case synthesis pipeline that decouples the generation into a three-step input generation method and a mutual verification mechanism for effective output labeling; (3) we augment problems with high-quality, test-case-verified long-reasoning solutions. Extensive experiments on Qwen models (1.5B-14B) across various code reasoning benchmarks demonstrate the superiority of rStar-Coder dataset, achieving leading performance comparable to frontier reasoning LLMs with much smaller model sizes. On LiveCodeBench, rStar-Coder improves Qwen2.5-7B from 17.4% to an impressive 57.3%, and Qwen2.5-14B from 23.3% to 62.5%, surpassing o3-mini (low) by3.1%. On the more challenging USA Computing Olympiad, our 7B model achieves an average pass@1 accuracy of 16.15%, outperforming the frontier-level QWQ-32B. Code and the dataset will be released at https://github.com/microsoft/rStar.