CWM：一款开源权重的大型语言模型，专为结合世界模型进行代码生成研究而设计

摘要

我们发布了Code World Model（CWM），这是一个拥有320亿参数的开源权重大语言模型，旨在推动基于世界模型的代码生成研究。为了超越仅通过静态代码训练所能达到的代码理解水平，我们对CWM进行了中期训练，使用了大量来自Python解释器和自主Docker环境的观察-行动轨迹数据，并在可验证编码、数学以及多轮软件工程环境中进行了广泛的多任务推理强化学习。通过CWM，我们为研究人员提供了一个强大的测试平台，以探索世界模型在计算环境中通过推理和规划改进代码生成所带来的机遇。我们展示了世界模型如何助力自主编码、实现Python代码执行的逐步模拟，并初步揭示了推理如何从后者中获益。CWM是一个密集的、仅解码器架构的大语言模型，训练时上下文长度可达131k个token。即便不考虑其世界建模能力，CWM在通用编码和数学任务上也表现出色：在SWE-bench Verified（含测试时扩展）上达到65.8%的pass@1分数，在LiveCodeBench上为68.6%，在Math-500上高达96.6%，在AIME 2024上则为76.0%。为了支持代码世界建模的进一步研究，我们发布了中期训练、监督微调（SFT）和强化学习（RL）后的模型检查点。

English

We release Code World Model (CWM), a 32-billion-parameter open-weights LLM, to advance research on code generation with world models. To improve code understanding beyond what can be learned from training on static code alone, we mid-train CWM on a large amount of observation-action trajectories from Python interpreter and agentic Docker environments, and perform extensive multi-task reasoning RL in verifiable coding, math, and multi-turn software engineering environments. With CWM, we provide a strong testbed for researchers to explore the opportunities world modeling affords for improving code generation with reasoning and planning in computational environments. We present first steps of how world models can benefit agentic coding, enable step-by-step simulation of Python code execution, and show early results of how reasoning can benefit from the latter. CWM is a dense, decoder-only LLM trained with a context size of up to 131k tokens. Independent of its world modeling capabilities, CWM offers strong performance on general coding and math tasks: it reaches pass@1 scores of 65.8% on SWE-bench Verified (with test-time scaling), 68.6% on LiveCodeBench, 96.6% on Math-500, and 76.0% on AIME 2024. To support further research on code world modeling, we release model checkpoints after mid-training, SFT, and RL.

CWM：一款开源权重的大型语言模型，专为结合世界模型进行代码生成研究而设计

CWM: An Open-Weights LLM for Research on Code Generation with World Models

摘要

Support