Paper Detail
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
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{li2026kat,
title = {KAT-Coder-V2 Technical Report},
author = {Fengxiang Li and Han Zhang and Haoyang Huang and Jinghui Wang and Jinhua Hao and Kun Yuan and Mengtong Li and Minglei Zhang and Pengcheng Xu and Wenhao Zhuang and Yizhen Shao and Zongxian Feng and Can Tang and Chao Wang and Chengxiao Tong and Fan Yang and Gang Xiong and Haixuan Gao and Han Gao and Hao Wang and Haochen Liu and Hongliang Sun and Jiabao Li and Jingwen Chang and Jun Du and Junyi Peng and Leizhen Cui and Meimei Jing and Mingqi Wu and Shangpeng Yan and Shaotong Qi and Suzhe Xu and Wenxuan Zhao and Xianda Sun and Xuan Xie and Yanbo Wang and Yao Xia and Yinghan Cui and Yingpeng Chen and Yong Wang and Yuze Shi and Zhiwei Shen and Ziyu Wang and Ming Sun and Lin Ye and Bin Chen},
year = {2026},
abstract = {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 san},
url = {https://arxiv.org/abs/2603.27703},
keywords = {cs.CL, cs.LG},
eprint = {2603.27703},
archiveprefix = {arXiv},
}
{}