快手开源了KAT-Coder-V2.5，用10万个可验证环境训练代码智能体。AutoBuilder把环境搭建成功率从16%拉到57%，沙盒审计又让反馈错误降到2%以下。做编程智能体训练的值得一看。
快手KwaiKAT团队发布技术报告，推出KAT-Coder-V2.5智能体编程模型，在10万个可验证仓库环境上训练。团队开发AutoBuilder工具，将环境构建成功率从16.5%提升至57.2%，覆盖12种编程语言。沙盒审计机制将强化学习反馈错误率从约16%降低至2%以下。研究指出，智能体编程能力的瓶颈在于训练基础设施而非模型规模。
KwaiKAT Team Releases KAT-Coder-V2.5: An Agentic Coding Model Trained on 100,000+ Verifiable Repository Environments
The KwaiKAT Team at Kuaishou has published the KAT-Coder-V2.5 technical report, arguing that agentic coding capability is bottlenecked by training infrastructure rather than model scale. AutoBuilder raised environment construction success from 16.5% to 57.2%, producing over 100,000 verifiable environments across 12 languages, while a sandbox audit cut RL feedback errors from roughly 16% to below 2%. The post KwaiKAT Team Releases KAT-Coder-V2.5: An Agentic Coding Model Trained on 100,000+ Verifiable Repository Environments appeared first on MarkTechPost .