tracked author

Shaohan Huang

LLM-in-Sandbox coauthor from Microsoft Research. Public homepage and Microsoft profile identify him as a Senior Researcher / Researcher in the Microsoft Research Asia GenAI group.

1 archived notes X: not-found Homepage GitHub

Related Notes

按论文归档时间排序，展示该作者在本站已经出现的材料。

归档 Jul 09, 2026

Computer Environments Elicit General Agentic Intelligence in LLMs

LLM in Sandbox 只给模型 shell、文件编辑和完成信号，使部分模型—任务组合获得最高 15.5 个百分点增益，并让 Qwen3 4B 经文件型通用任务强化学习后把平均交互轮次从 23.7 降到 7.0，这些数值来自允许联网的特定环境配置。

待审阅 2601.16206-computer-environments-agentic-intelligence Tool Use Agent RL Agent Workflow