OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique

• URL: http://arxiv.org/abs/2507.09075v1
• Date: Fri, 11 Jul 2025 23:35:54 GMT
• Title: OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique
• Authors: Wasi Uddin Ahmad, Somshubra Majumdar, Aleksander Ficek, Sean Narenthiran, Mehrzad Samadi, Jocelyn Huang, Siddhartha Jain, Vahid Noroozi, Boris Ginsburg,
• Abstract summary: We introduce OpenCodeReasoning-II, a dataset consisting of 2.5M question-solution-critique triples (approx. 35K unique programming questions)<n>In this work, we employ a two-stage supervised fine-tuning strategy. The first stage focuses on fine-tuning for code generation, while the second stage involves the joint training of models for both code generation and critique. Notably, the integration of our code generation and critique models leads to significant improvements in competitive coding performance.
• Score: 59.18475981916166
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advancements in reasoning-based Large Language Models (LLMs), particularly their potential through test-time scaling, have created significant opportunities for distillation in code generation and critique. However, progress in both areas fundamentally depends on large-scale, high-quality datasets. In this work, we introduce OpenCodeReasoning-II, a dataset consists of 2.5M question-solution-critique triples (approx. 35K unique programming questions), making it nearly twice the size of the previous largest publicly available code reasoning dataset. In this work, we employ a two-stage supervised fine-tuning strategy. The first stage focuses on fine-tuning for code generation, while the second stage involves the joint training of models for both code generation and critique. Our resulting finetuned Qwen2.5-Instruct models achieve performance in code generation that either exceeds or equals the best prior open-weight distilled models. Notably, the integration of our code generation and critique models leads to significant improvements in competitive coding performance. Furthermore, we present an extension of the LiveCodeBench benchmark to specifically support the C++ programming language, thereby facilitating more comprehensive LLM evaluation using this benchmark.

Related papers

• Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM [43.77512279007385]
  Ling-Coder-Lite is a code large language model with comprehensive performance yet ultimate efficiency.<n>We leverage the efficient Mixture-of-Experts (MoE) architecture along with a set of high-quality data curation methods.<n>Ling-Coder-Lite exhibits on-par performance on 12 representative coding benchmarks compared to state-of-the-art models of similar size.
  arXiv  Detail & Related papers  (2025-03-22T15:00:18Z)
• Robust Learning of Diverse Code Edits [10.565439872488328]
  Software engineering activities frequently involve edits to existing code.<n>Code language models (LMs) lack the ability to handle diverse types of code-edit requirements.<n>We propose a novel synthetic data generation pipeline and an adaptation algorithm.
  arXiv  Detail & Related papers  (2025-03-05T16:39:04Z)
• Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation [69.62857948698436]
  Recent advances in large language models (LLMs) have improved their performance on coding benchmarks.<n>However, improvement is plateauing due to the exhaustion of readily available high-quality data.<n>We propose Sol-Ver, a self-play solver-verifier framework that jointly improves a single model's code and test generation capacity.
  arXiv  Detail & Related papers  (2025-02-20T18:32:19Z)
• UnitCoder: Scalable Iterative Code Synthesis with Unit Test Guidance [65.01483640267885]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet code generation remains a major challenge.<n>We introduce UnitCoder, a systematic pipeline leveraging model-generated unit tests to guide and validate the code generation process.<n>Our work presents a scalable approach that leverages model-generated unit tests to guide the synthesis of high-quality code data from pre-training corpora.
  arXiv  Detail & Related papers  (2025-02-17T05:37:02Z)
• Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation [5.6001617185032595]
  Large language models pretrained on both programming and natural language data tend to perform well in code-oriented tasks. We fine-tune open-source Large language models (LLM) in parameter-efficient, quantized low-rank fashion on consumer-grade hardware to improve review comment generation.
  arXiv  Detail & Related papers  (2024-11-15T12:01:38Z)
• OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models [76.59316249991657]
  Large language models (LLMs) for code have become indispensable in various domains, including code generation, reasoning tasks and agent systems.<n>While open-access code LLMs are increasingly approaching the performance levels of proprietary models, high-quality code LLMs remain limited.<n>We introduce OpenCoder, a top-tier code LLM that not only achieves performance comparable to leading models but also serves as an "open cookbook" for the research community.
  arXiv  Detail & Related papers  (2024-11-07T17:47:25Z)
• VersiCode: Towards Version-controllable Code Generation [58.82709231906735]
  Large Language Models (LLMs) have made tremendous strides in code generation, but existing research fails to account for the dynamic nature of software development. We propose two novel tasks aimed at bridging this gap: version-specific code completion (VSCC) and version-aware code migration (VACM) We conduct an extensive evaluation on VersiCode, which reveals that version-controllable code generation is indeed a significant challenge.
  arXiv  Detail & Related papers  (2024-06-11T16:15:06Z)
• LLM-Assisted Code Cleaning For Training Accurate Code Generators [53.087019724256606]
  We investigate data quality for code and find that making the code more structured and readable leads to improved code generation performance of the system. We build a novel data-cleaning pipeline that uses these principles to transform existing programs. We evaluate our approach on two challenging algorithmic code generation benchmarks and find that fine-tuning CodeLLaMa-7B improves the performance by up to 30% compared to fine-tuning on the original dataset.
  arXiv  Detail & Related papers  (2023-11-25T02:45:50Z)
• Better Language Models of Code through Self-Improvement [18.75015225501755]
  We propose a simple data augmentation framework for pre-trained language models for code (PLMCs) Our framework utilizes knowledge gained during the pre-training and fine-tuning stage to generate pseudo data, which is then used as training data for the next step. The results show that our framework significantly improves PLMCs' performance in code-related sequence generation tasks.
  arXiv  Detail & Related papers  (2023-04-02T10:59:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.