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
摘要
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 .
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper3
- Co-designing Large Language Model Tools for Project-Based Learning with K12 EducatorsPrerna Ravi, John Masla, Gisella Kakoti, Grace C. Lin 等CHI 2025 · 被引用 26 次
- AutoPBL: An LLM-powered Platform to Guide and Support Individual Learners Through Self Project-based LearningYihao Zhu, Zhoutong Ye, Yichen Yuan, Wenxuan Tang 等CHI 2025 · 被引用 17 次
- ReAct: Synergizing Reasoning and Acting in Language ModelsShunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du 等ICLR 2023
相关 Paper
- We are the Greatest Showmen: Configuring a Framework for Project-Based Mobile LearningDan Richardson, Ahmed KharrufaCHI 2020 · 被引用 8 次
- Charting the Future of AI in Project-Based Learning: A Co-Design Exploration with StudentsChengbo Zheng, Kangyu Yuan, Bingcan Guo, Reza Hadi Mogavi 等CHI 2024 · 被引用 65 次
- Experiential Co-Learning of Software-Developing AgentsChen Qian, Yufan Dang, Jiahao Li, Wei Liu 等ACL 2024
- DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent BehaviorsRui Sheng, Yukun Yang, Chuhan Shi, Yanna Lin 等CHI 2026 · 被引用 2 次
- Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and ImproveYuanzhe Liu, Ryan Deng, Tim Kaler, Xuhao Chen 等NeurIPS 2025
