GLM-5实现从感知编码到自主工程的跃迁，大幅降低训练成本。
GLM-5: from Vibe Coding to Agentic Engineering
- 采用DSA技术降低训练与推理开销，保持长上下文精度。
- 异步强化学习提升后训练效率，支持复杂长期任务学习。
- 在真实软件工程任务中表现超越此前模型，具备端到端能力。
我们提出GLM-5，一种新一代基础模型，旨在推动从‘vibe coding’向‘agentic engineering’范式转变。基于前代模型的代理、推理与编码（ARC）能力，GLM-5引入DSA技术，显著降低训练与推理成本，同时维持长上下文一致性。为提升模型对齐与自主性，我们构建了新型异步强化学习基础设施，通过解耦生成与训练过程，大幅提升后训练效率。此外，提出新颖的异步代理强化学习算法，进一步提升强化学习质量，使模型能更有效学习复杂、长时程交互。通过这些创新，GLM-5在主流开源基准上达到最先进水平。最关键的是，其在真实编码任务中展现出前所未有的能力，显著优于以往基线，可应对端到端软件工程挑战。代码、模型及更多信息见 https://github.com/zai-org/GLM-5。
原文摘要 · Abstract (English)
We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context fidelity. To advance model alignment and autonomy, we implement a new asynchronous reinforcement learning infrastructure that drastically improves post-training efficiency by decoupling generation from training. Furthermore, we propose novel asynchronous agent RL algorithms that further improve RL quality, enabling the model to learn from complex, long-horizon interactions more effectively. Through these innovations, GLM-5 achieves state-of-the-art performance on major open benchmarks. Most critically, GLM-5 demonstrates unprecedented capability in real-world coding tasks, surpassing previous baselines in handling end-to-end software engineering challenges. Code, models, and more information are available at https://github.com/zai-org/GLM-5.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。