Qwen3-Coder-Next 技术报告
Qwen3-Coder-Next Technical Report
AI总结:
Qwen3-Coder-Next通过高效推理和代理训练技术,在小参数量下实现强大的编码能力,适用于研究和实际应用。
摘要:
我们提出了Qwen3-Coder-Next,一个专为编码代理设计的开放权重语言模型。Qwen3-Coder-Next是一个800亿参数的模型,在推理过程中仅激活30亿参数,使其在高效推理的同时具备强大的编码能力。在本研究中,我们探索了强大的训练配方如何推动参数 footprint 较小的模型的能力极限。为此,我们通过大规模合成可验证的编码任务与可执行环境的结合,进行代理训练,允许在中期训练和强化学习中直接从环境反馈中学习。在包括SWE-Bench和Terminal-Bench在内的代理导向基准测试中,Qwen3-Coder-Next在与激活参数数量相对应的情况下实现了具有竞争力的性能。我们发布了基础版和指令微调版的开放权重版本,以支持研究和实际的编码代理开发。
英文摘要:
We present Qwen3-Coder-Next, an open-weight language model specialized for coding agents. Qwen3-Coder-Next is an 80-billion-parameter model that activates only 3 billion parameters during inference, enabling strong coding capability with efficient inference. In this work, we explore how far strong training recipes can push the capability limits of models with small parameter footprints. To achieve this, we perform agentic training through large-scale synthesis of verifiable coding tasks paired with executable environments, allowing learning directly from environment feedback via mid-training and reinforcement learning. Across agent-centric benchmarks including SWE-Bench and Terminal-Bench, Qwen3-Coder-Next achieves competitive performance relative to its active parameter count. We release both base and instruction-tuned open-weight versions to support research and real-world coding agent development.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。