DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation

• URL: http://arxiv.org/abs/2506.20639v2
• Date: Thu, 26 Jun 2025 15:46:40 GMT
• Title: DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
• Authors: Shansan Gong, Ruixiang Zhang, Huangjie Zheng, Jiatao Gu, Navdeep Jaitly, Lingpeng Kong, Yizhe Zhang,
• Abstract summary: Diffusion large language models (dLLMs) are compelling alternatives to autoregressive (AR) models.<n>We investigate their denoising processes and reinforcement learning methods.<n>Our work provides deeper insight into the machinery of dLLM generation and offers an effective, diffusion-native RL training framework.
• Score: 68.19756761027351
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Diffusion large language models (dLLMs) are compelling alternatives to autoregressive (AR) models because their denoising models operate over the entire sequence. The global planning and iterative refinement features of dLLMs are particularly useful for code generation. However, current training and inference mechanisms for dLLMs in coding are still under-explored. To demystify the decoding behavior of dLLMs and unlock their potential for coding, we systematically investigate their denoising processes and reinforcement learning (RL) methods. We train a 7B dLLM, \textbf{DiffuCoder}, on 130B tokens of code. Using this model as a testbed, we analyze its decoding behavior, revealing how it differs from that of AR models: (1) dLLMs can decide how causal their generation should be without relying on semi-AR decoding, and (2) increasing the sampling temperature diversifies not only token choices but also their generation order. This diversity creates a rich search space for RL rollouts. For RL training, to reduce the variance of token log-likelihood estimates and maintain training efficiency, we propose \textbf{coupled-GRPO}, a novel sampling scheme that constructs complementary mask noise for completions used in training. In our experiments, coupled-GRPO significantly improves DiffuCoder's performance on code generation benchmarks (+4.4\% on EvalPlus) and reduces reliance on AR bias during decoding. Our work provides deeper insight into the machinery of dLLM generation and offers an effective, diffusion-native RL training framework. https://github.com/apple/ml-diffucoder.

Related papers

• ReVeal: Self-Evolving Code Agents via Iterative Generation-Verification [6.983144806500892]
  ReVeal is a multi-turn reinforcement learning framework that interleaves code generation with explicit self-verification and tool-based evaluation.<n>It fosters the co-evolution of a model's generation and verification capabilities through RL training, expanding the reasoning boundaries of the base model.<n>It also enables test-time scaling into deeper inference regimes, with code consistently evolving as the number of turns increases during inference.
  arXiv  Detail & Related papers  (2025-06-13T03:41:04Z)
• VerIF: Verification Engineering for Reinforcement Learning in Instruction Following [55.60192044049083]
  Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing large language models (LLMs)<n>We propose VerIF, a verification method that combines rule-based code verification with LLM-based verification from a large reasoning model.<n>We apply RL training with VerIF to two models, achieving significant improvements across several representative instruction-following benchmarks.
  arXiv  Detail & Related papers  (2025-06-11T17:10:36Z)
• Scaling Offline RL via Efficient and Expressive Shortcut Models [13.050231036248338]
  offline reinforcement learning (RL) remains challenging due to the iterative nature of their noise sampling processes.<n>We introduce Scalable Offline Reinforcement Learning (SORL), a new offline RL algorithm that leverages shortcut models to scale both training and inference.<n>We demonstrate that SORL achieves strong performance across a range of offline RL tasks and exhibits positive scaling behavior with increased test-time compute.
  arXiv  Detail & Related papers  (2025-05-28T20:59:22Z)
• d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning [31.531278643184656]
  Recent large language models (LLMs) have demonstrated strong reasoning capabilities that benefits from online reinforcement learning (RL)<n>We propose d1, a framework to adapt pre-trained masked dLLMs into reasoning models via a combination of supervised finetuning (SFT) and RL.<n>We find that d1 yields the best performance and significantly improves performance of a state-of-the-art dLLM.
  arXiv  Detail & Related papers  (2025-04-16T16:08:45Z)
• Exploring Training and Inference Scaling Laws in Generative Retrieval [50.82554729023865]
  Generative retrieval reformulates retrieval as an autoregressive generation task, where large language models generate target documents directly from a query.<n>We systematically investigate training and inference scaling laws in generative retrieval, exploring how model size, training data scale, and inference-time compute jointly influence performance.
  arXiv  Detail & Related papers  (2025-03-24T17:59:03Z)
• 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)
• Process Supervision-Guided Policy Optimization for Code Generation [15.943210767010045]
  Reinforcement learning (RL) with unit test feedback has enhanced large language models' (LLMs) code generation, but relies on sparse rewards provided only after complete code evaluation.<n>We propose a Process Reward Model (PRM) that delivers dense, line-level feedback on code correctness during generation, mimicking human code refinement.
  arXiv  Detail & Related papers  (2024-10-23T07:22:33Z)
• COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement [80.18490952057125]
  Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. We propose Context-Wise Order-Agnostic Language Modeling (COrAL) to overcome these challenges. Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally.
  arXiv  Detail & Related papers  (2024-10-12T23:56:19Z)
• StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback [58.20547418182074]
  We introduce StepCoder, a novel framework for code generation, consisting of two main components. CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks. FGO only optimize the model by masking the unexecuted code segments to provide Fine-Grained Optimization. Our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
  arXiv  Detail & Related papers  (2024-02-02T13:14:31Z)
• RLTF: Reinforcement Learning from Unit Test Feedback [17.35361167578498]
  Reinforcement Learning from Unit Test Feedback is a novel online RL framework with unit test feedback of multi-granularity for refining code LLMs. Our approach generates data in real-time during training and simultaneously utilizes fine-grained feedback signals to guide the model towards producing higher-quality code.
  arXiv  Detail & Related papers  (2023-07-10T05:18:18Z)

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.