Kou Shi

1. 2026

   Intern-S2-Preview: Scientific Agentic Foundation Model

   Lei Bai et al., with Kou Shi as a contributor

   A technical report on scientific agentic foundation models for multimodal understanding, reasoning, generation, and long-horizon tasks.

   arXiv:2608.13505
2. 2026

   AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios

   Kou Shi, Ziao Zhang, Shiting Huang, Avery Nie, Zhen Fang, Qiuchen Wang, Lin Chen, Huaian Chen, Zehui Chen, Feng Zhao

   A benchmark for asynchronous function calling, dependency tracking, and coordination under multi-task workloads and tool latency.

   arXiv:2605.27995
3. 2026

   SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering

   Qingnan Ren, Shun Zou, Shiting Huang, Ziao Zhang, Kou Shi, Zhen Fang, Yiming Zhao, Yu Zeng, Qisheng Su, Lin Chen, Yong Wang, Zehui Chen, Xiangxiang Chu, Feng Zhao

   A benchmark for coding agents in long-horizon enterprise SaaS engineering across heterogeneous stacks and system-level integration.

   arXiv:2605.17526
4. 2026

   SkillFlow: Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents

   Ziao Zhang, Kou Shi, Shiting Huang, Avery Nie, Yu Zeng, Yiming Zhao, Zhen Fang, Qishen Su, Haibo Qiu, Wei Yang, Qingnan Ren, Shun Zou, Wenxuan Huang, Lin Chen, Zehui Chen, Feng Zhao

   A benchmark for how autonomous agents discover, repair, transfer, and maintain skills over sequential experience.

   arXiv:2604.17308
5. 2026

   Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models

   Shiting Huang, Zecheng Li, Yu Zeng, Qingnan Ren, Zhen Fang, Qisheng Su, Kou Shi, Lin Chen, Zehui Chen, Feng Zhao

   Internalizing error-derived meta-experience into parametric memory to improve reusable reasoning knowledge.

   arXiv:2602.10224

Research involving my broader group is listed separately from papers on which I am a named author.