ACL2026

SimPBL: A Multi-Agent Framework for Project-Based Learning

Daniel Zhang-Li, Joy Lim Jia Yin, Binglin Liu, Shangqing Tu, Zijun Yao, Hao Peng, Jifan Yu, Haoxuan Li, Zhanxin Hao, Ye He, Zekun Li, Jiangyi Wang, Lei Hou, Bin Xu, Xin Cong, Zhiyuan Liu, Huiqin Liu, Yu Zhang, Juanzi Li

Abstract

Project-Based Learning (PBL) is an important learning method that promotes understanding and the acquisition of practical skills by training learners through a project. Such effectiveness in PBL often depends on sustained orchestration and collaboration. However, existing LLM-based learning tools provide partial assistance without explicitly modeling these roles, and overly comprehensive help provided by LLM can reduce learner autonomy. We propose SIMPBL, a multi-agent framework with an orchestrator agent that provides adaptive scaffolding from interaction logs and collaborator agents that support project work through boundary-aware collaboration. We conduct comprehensive evaluations to study the effectiveness of SIMPBL, where we observe a 14% improvement in learner examination score. Results from extensive studies further highlight the ability of SIMPBL to manage learning behavior and improve the learning experience. Code and materials are available at https:// github.com/THU-MAIC/OpenMAIC-Project .