dorsal/arxiv
View SchemaX-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests
| Authors | Jie Wu, Haoling Li, Xin Zhang, Jiani Guo, Jane Luo, Steven Liu, Yangyu Huang, Ruihang Chu, Scarlett Li, Yujiu Yang |
|---|---|
| Categories | |
| ArXiv ID | 2601.06953vv1 |
| URL | https://arxiv.org/abs/2601.06953 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
Competitive programming presents great challenges for Code LLMs due to its intensive reasoning demands and high logical complexity. However, current Code LLMs still rely heavily on real-world data, which limits their scalability. In this paper, we explore a fully synthetic approach: training Code LLMs with entirely generated tasks, solutions, and test cases, to empower code reasoning models without relying on real-world data. To support this, we leverage feature-based synthesis to propose a novel data synthesis pipeline called SynthSmith. SynthSmith shows strong potential in producing diverse and challenging tasks, along with verified solutions and tests, supporting both supervised fine-tuning and reinforcement learning. Based on the proposed synthetic SFT and RL datasets, we introduce the X-Coder model series, which achieves a notable pass rate of 62.9 avg@8 on LiveCodeBench v5 and 55.8 on v6, outperforming DeepCoder-14B-Preview and AReal-boba2-14B despite having only 7B parameters. In-depth analysis reveals that scaling laws hold on our synthetic dataset, and we explore which dimensions are more effective to scale. We further provide insights into code-centric reinforcement learning and highlight the key factors that shape performance through detailed ablations and analysis. Our findings demonstrate that scaling high-quality synthetic data and adopting staged training can greatly advance code reasoning, while mitigating reliance on real-world coding data.
{
"annotation_id": "eae279fd-2bf0-4c64-84c0-1eb0f48d2e75",
"date_created": "2026-02-17T05:53:08.161000Z",
"date_modified": "2026-02-17T05:53:08.161000Z",
"file_hash": "d3c62d0ac7825ca156c12d34b1978cf92b10770a07d042ce1e2e3ca4bf8c4710",
"private": false,
"record": {
"abstract": "Competitive programming presents great challenges for Code LLMs due to its intensive reasoning demands and high logical complexity. However, current Code LLMs still rely heavily on real-world data, which limits their scalability. In this paper, we explore a fully synthetic approach: training Code LLMs with entirely generated tasks, solutions, and test cases, to empower code reasoning models without relying on real-world data. To support this, we leverage feature-based synthesis to propose a novel data synthesis pipeline called SynthSmith. SynthSmith shows strong potential in producing diverse and challenging tasks, along with verified solutions and tests, supporting both supervised fine-tuning and reinforcement learning. Based on the proposed synthetic SFT and RL datasets, we introduce the X-Coder model series, which achieves a notable pass rate of 62.9 avg@8 on LiveCodeBench v5 and 55.8 on v6, outperforming DeepCoder-14B-Preview and AReal-boba2-14B despite having only 7B parameters. In-depth analysis reveals that scaling laws hold on our synthetic dataset, and we explore which dimensions are more effective to scale. We further provide insights into code-centric reinforcement learning and highlight the key factors that shape performance through detailed ablations and analysis. Our findings demonstrate that scaling high-quality synthetic data and adopting staged training can greatly advance code reasoning, while mitigating reliance on real-world coding data.",
"arxiv_id": "2601.06953",
"authors": [
"Jie Wu",
"Haoling Li",
"Xin Zhang",
"Jiani Guo",
"Jane Luo",
"Steven Liu",
"Yangyu Huang",
"Ruihang Chu",
"Scarlett Li",
"Yujiu Yang"
],
"categories": [
"cs.CL",
"cs.LG"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests",
"url": "https://arxiv.org/abs/2601.06953",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "52d0b2c9-7af2-433d-87e5-8f62f3b87fec",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}