AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents

8月 1, 2026·
Shengda Fan
,
Xuyan Ye
,
Yupeng Huo
,
Zhi-Yuan Chen
,
Yiju Guo
,
Shenzhi Yang
,
Wenkai Yang
,
Shuqi Ye
,
Jingwen Chen
Haotian Chen
Haotian Chen
,
Xin Cong
,
Yankai Lin
Corresponding author
· 0 分钟阅读时长
摘要
We introduce AgentProcessBench, a benchmark that diagnoses the step-level process quality of tool-using agents rather than only their final outcomes.
类型
出版物
In Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2026)
publications
Haotian Chen
Authors
Research Assistant Professor · LLM Post-Training / AI4AI
I am a Research Assistant Professor at the School of Artificial Intelligence, Shanghai Jiao Tong University, where I work with Prof. Junchi Yan at RethinkLab. I study how to build AI systems that can automate long-horizon, effort-intensive, and creativity-demanding tasks such as research, engineering, and development. My current work focuses on LLM post-training for autonomous agents, agent memory and continual learning, and AI4Research / AI4AI. Before joining SJTU, I received my PhD in Data Science from Fudan University, advised by Prof. Xiangdong Zhou, and completed postdoctoral research at Tsinghua University (THUNLP), working with Prof. Zhiyuan Liu and Prof. Maosong Sun. I was also a research intern at the Machine Learning Research Group of Microsoft Research Asia, mentored by Xiao Yang, and at the Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University, working with Prof. Yang Yu.