mlsanityData to 7 Oct 2026

X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests

arXiv 2601.06953 ↗First posted 11 Jan 2026cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Competitive programming remains challenging for code LLMs. Despite recent progress, many training pipelines still depend on scarce real-world data, raising concerns about scalability and near-duplicate benchmark contamination. In this paper, we examine whether synthetic training artifacts can support the complete SFT-to-RL cycle for competitive programming: no real-world tasks, solutions, or test cases are directly used for post-training. To this end, we synthesize tasks, verified solutions, and reliable test cases that serve as reward signals for reinforcement learning. To improve reward reliability, we introduce a dual-verification strategy that reduces noise in both selected solutions and test outputs. Using this high-quality data, we train the X-Coder model series. X-Coder-14B achieves 67.5% avg@8 on LiveCodeBench v5 and 63.4% on v6, outperforming its base model by over 40 points. Further analysis provides practical insights into synthetic post-training, highlighting the value of diverse tasks, verified long-CoT supervision, and code-centric reinforcement. Our data and models are released at https://github.com/JieWu02/X-Coder

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 55 references that are in the map. First posted on arXiv 11 Jan 2026.

Builds on

37 of 55 references.

References · 37

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2021Program Synthesis with Large Language Modelscited by 3,509
  5. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  6. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  7. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  8. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  9. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,057
  10. 2021Measuring Coding Challenge Competence With APPScited by 879
  11. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 728
  12. 2025Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRscited by 373
25 more
  1. 2025OpenThoughts: Data Recipes for Reasoning Modelscited by 287
  2. 2025SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolutioncited by 246
  3. 2024LiveBench: A Challenging, Contamination-Limited LLM Benchmarkcited by 242
  4. 2025AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoningcited by 234
  5. 2025KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Codingcited by 115
  6. 2025OpenCodeReasoning: Advancing Data Distillation for Competitive Codingcited by 106
  7. 2025ACECODER: Acing Coder RL via Automated Test-Case Synthesiscited by 89
  8. 2025AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergycited by 75
  9. 2024SelfCodeAlign: Self-Alignment for Code Generationcited by 61
  10. 2025rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Datasetcited by 49
  11. 2023WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuningcited by 42
  12. 2025CodeContests+: High-Quality Test Case Generation for Competitive Programmingcited by 39
  13. 2025Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimizationcited by 39
  14. 2024Process Supervision-Guided Policy Optimization for Code Generationcited by 25
  15. 2025HardTests: Synthesizing High-Quality Test Cases for LLM Codingcited by 22
  16. 2025COFFE: A Code Efficiency Benchmark for Code Generationcited by 18
  17. 2025RPG: A Repository Planning Graph for Unified and Scalable Codebase Generationcited by 18
  18. 2025Rethinking Verification for LLM Code Generation: From Generation to Testingcited by 12
  19. 2025AutoCode: LLMs as Problem Setters for Competitive Programmingcited by 11
  20. 2025Can LLMs Generate High-Quality Test Cases for Algorithm Problems? TestCase-Eval: A Systematic Evaluation of Fault Coverage and Exposurecited by 10
  21. 2025Can LLMs Generate Reliable Test Case Generators? A Study on Competition-Level Programming Problemscited by 9
  22. 2025Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learningcited by 9
  23. 2025LogiCase: Effective Test Case Generation from Logical Description in Competitive Programmingcited by 4
  24. 2025CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedbackcited by 4
  25. 2025Codehacks: A Dataset of Adversarial Tests for Competitive Programming Problems Obtained from Codeforcescited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
  2. 2025Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
  3. 2026Reinforcement Learning for Code Optimization
  4. 2026Post-Training Language Models for Gold-Medal Performance in Coding Competitions
  5. 2026GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
  6. 2024RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning
  7. 2025Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning
  8. 2025DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation