Publications

Yuepeng Fu, Zhong Zhang, Xin Cong, Shengda Fan, Yesai Wu, Yaxi Lu, Haotian Chen

Corresponding author

, Yankai Lin, Chen Qian, Xiaoyin Che (2026). Learning from Human Demonstrations Enables Adaptive GUI Agents. ARR (pre-submission).

Wentong Chen, Xin Cong, Zhong Zhang, Yaxi Lu, Siyuan Zhao, Yesai Wu, Qinyu Luo, Haotian Chen

Corresponding author

Corresponding author

, Zhiyuan Liu, Maosong Sun (2026). Test-Time Exploration in Unknown Environments. KDD 2026 (submitted).

Shengda Fan, Xuyan Ye, Yupeng Huo, Zhi-Yuan Chen, Yiju Guo, Shenzhi Yang, Wenkai Yang, Shuqi Ye, Jingwen Chen, Haotian Chen

Corresponding author

, Xin Cong, Yankai Lin (2026). AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents. KDD 2026 (submitted).

Equal contribution

Equal contribution

Equal contribution

Equal contribution

Equal contribution

, Yaxi Lu, Zhong Zhang, Xin Cong, Yankai Lin, Zhiyuan Liu, Maosong Sun (2026). ToLeaP: Rethinking Development of Tool Learning with Large Language Models. ACL 2026 (submitted).

Equal contribution

Equal contribution

Equal contribution

, Yaxi Lu, Xin Cong, Zhong Zhang, Yankai Lin, Zhiyuan Liu, Maosong Sun (2026). Reflective Reinforcement Tool Learning. ACL 2026 (submitted).

Bohan Lyu, Qixin Xu, Zihan Zhu, Yesai Wu, Zhong Zhang

Corresponding author

Corresponding author

, Xin Cong, Xiaojiang Liu, Zhiyuan Liu, Maosong Sun (2026). Diversity-aware Training for Test-time Scaling. ACL 2026 (submitted).

Yupeng Huo, Yaxi Lu, Zhong Zhang, Haotian Chen

Corresponding author

, Yankai Lin (2026). AtomMem: Learnable Dynamic Agentic Memory with Atomic Memory Operation. ACL 2026 (submitted).

Equal contribution

Equal contribution

, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, et al., Zhiyuan Liu, Maosong Sun (2025). AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning. In EMNLP 2025 Demo.

MiniCPM Team, Haotian Chen, et al. (2025). MiniCPM4: Ultra-Efficient LLMs on End Devices. ArXiv 2025.