KAT-Coder-V2 技术报告

KAT-Coder-V2 Technical Report

March 29, 2026

作者: Fengxiang Li, Han Zhang, Haoyang Huang, Jinghui Wang, Jinhua Hao, Kun Yuan, Mengtong Li, Minglei Zhang, Pengcheng Xu, Wenhao Zhuang, Yizhen Shao, Zongxian Feng, Can Tang, Chao Wang, Chengxiao Tong, Fan Yang, Gang Xiong, Haixuan Gao, Han Gao, Hao Wang, Haochen Liu, Hongliang Sun, Jiabao Li, Jingwen Chang, Jun Du, Junyi Peng, Leizhen Cui, Meimei Jing, Mingqi Wu, Shangpeng Yan, Shaotong Qi, Suzhe Xu, Wenxuan Zhao, Xianda Sun, Xuan Xie, Yanbo Wang, Yao Xia, Yinghan Cui, Yingpeng Chen, Yong Wang, Yuze Shi, Zhiwei Shen, Ziyu Wang, Ming Sun, Lin Ye, Bin Chen

cs.AI

摘要

我们推出KAT-Coder-V2——由快手KwaiKAT团队研发的智能体编码模型。该模型采用"先专精后统一"范式，将智能体编码分解为SWE（软件工程）、网页编程、终端操作、网络搜索及通用任务五大专家领域，各领域先经过独立的监督微调与强化学习训练，再通过同策略蒸馏技术融合为单一模型。我们开发了模块化基础设施KwaiEnv，可支撑数万个并发沙箱实例运行，并沿任务复杂度、意图对齐和支架泛化三个维度扩展强化学习训练。针对混合专家模型的强化学习稳定性问题，我们提出MCLA方法；针对树状轨迹的冗余计算问题，提出树状训练法，最高可实现6.2倍加速。KAT-Coder-V2在SWE-bench Verified上达到79.6%（对比Claude Opus的80.8%），PinchBench得分88.7（超越GLM-5和MiniMax M2.7），在三大前端美学场景中均位列第一，并在Terminal-Bench Hard（46.8分）与tau²-Bench（93.9分）上保持强劲的综合表现。模型已开源发布于https://streamlake.com/product/kat-coder。

English

We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou. KAT-Coder-V2 adopts a "Specialize-then-Unify" paradigm that decomposes agentic coding into five expert domains - SWE, WebCoding, Terminal, WebSearch, and General - each undergoing independent supervised fine-tuning and reinforcement learning, before being consolidated into a single model via on-policy distillation. We develop KwaiEnv, a modular infrastructure sustaining tens of thousands of concurrent sandbox instances, and scale RL training along task complexity, intent alignment, and scaffold generalization. We further propose MCLA for stabilizing MoE RL training and Tree Training for eliminating redundant computation over tree-structured trajectories with up to 6.2x speedup. KAT-Coder-V2 achieves 79.6% on SWE-bench Verified (vs. Claude Opus 4.6 at 80.8%), 88.7 on PinchBench (surpassing GLM-5 and MiniMax M2.7), ranks first across all three frontend aesthetics scenarios, and maintains strong generalist scores on Terminal-Bench Hard (46.8) and tau^2-Bench (93.9). Our model is publicly available at https://streamlake.com/product/kat-coder.