tracked author

Wayne Xin Zhao

LLM-in-Sandbox coauthor from RUC GSAI. RUC faculty page and Scholar profile identify him as a professor at Renmin University of China working on recommender systems, data mining and natural language processing, with PhD from Peking University.

2 archived notes X: not-found Homepage

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。

Jul 13, 2026

Agentic RL Learned Environment 演进路线：从可执行 Sandbox 到可校准世界模型

Agentic RL 的环境供给在 2024 2026 年经历了从统一可复位 sandbox、有状态用户与工具模拟、代码驱动环境合成，到用真实交互轨迹训练 language world model 的连续演进；当前证据最支持 real environment 提供状态与验证锚点、learned environment 扩大低成本 rollout、周期性真实交互修正分布偏移的混合闭环。

2026-07-13-agentic-rl-learned-environment-evolution Learned Environment Agent RL Tool Use

Jul 09, 2026

Computer Environments Elicit General Agentic Intelligence in LLMs

LLM in Sandbox 的核心贡献是把通用计算机抽象成一个最小 Docker code sandbox，并证明强模型在 training free 设置下能利用外部资源访问、文件管理和代码执行三类 meta capability 提升数学、物理、化学、长上下文和指令遵循等非代码任务；进一步的 LLM in Sandbox RL 说明，把一般 context based 数据放进文件系统并用 outcome reward 训练，可...

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