CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RLCuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RL

Preprint2025

Xinji Mai^*, Yunpeng Zhai^*, Ziqian Chen, Cheng Chen, Anni Zou, Shuchang Tao, Zhaoyang Liu, Bolin Ding

Figure from the 图片来源：original paper原论文 ↗

Curiosity-guided exploration grounds synthetic tasks in executable environments for agentic reinforcement learning.

以好奇心引导环境探索，在可执行的环境中合成智能体强化学习任务。