Existing ITSs rely on static curricula and reactive responses, lacking the ability to proactively guide learners toward specific professional objectives.
Goal & Profile Initialization
Skill Gap Identification
Learning Path Scheduling
Learning Content Creation
Dynamic Learner Profile
Abstract
Intelligent Tutoring Systems (ITSs) have revolutionized education by offering personalized learning experiences. However, as goal-oriented learning, which emphasizes efficiently achieving specific objectives, becomes increasingly important in professional contexts, existing ITSs often struggle to deliver this type of targeted learning experience. In this paper, we propose GenMentor, an LLM-powered multi-agent framework designed to deliver goal-oriented, personalized learning within ITS. GenMentor begins by accurately mapping learners' goals to required skills using a fine-tuned LLM trained on a custom goal-to-skill dataset. After identifying the skill gap, it schedules an efficient learning path using an evolving optimization approach, driven by a comprehensive and dynamic profile of learners' multifaceted status. Additionally, GenMentor tailors learning content with an exploration-drafting-integration mechanism to align with individual learner needs. Extensive automated and human evaluations demonstrate GenMentor's effectiveness in learning guidance and content quality. Furthermore, we have deployed it in practice and also implemented it as an application. Practical human study with professional learners further highlights its effectiveness in goal alignment and resource targeting, leading to enhanced personalization.
Goal-oriented Learning
Limitations of Traditional ITS
Professional Learning Needs
Modern professionals acquire targeted skills for specific goals; without clear guidance, the motivation and efficiency of learners may decline.
Goal-oriented Learning
Our approach emphasizes efficient goal achievement through personalized skill identification, adaptive learning paths, and targeted content delivery.
Evolution of ITS Paradigms
GenMentor Framework
Skill Gap Identification
Dataset Construction
- Custom goal-to-skill dataset
- Build from job postings
- CoT reasoning tracks
LLM Fine-tuning
- Goal-aligned skill mapping
- Improved accuracy & relevance
- Enhanced goal alignment
Gap Analysis
- Skill competency assessment
- Systematic gap identification
- Obtain skill & level gap
Adaptive Learner Modeling
Cognitive Status
- Learning progress tracking
- Skill mastery assessment
- Knowledge retention analysis
Learning Preferences
- Content style preferences
- Activity type preferences
- Learning pace optimization
Behavioral Patterns
- Usage patterns analysis
- Engagement metrics tracking
- Adaptive feedback system
Personalized Resource Delivery
Learning Path
- Evolving optimization method
- Learner simulator feedback
- Dynamic path adjustment
Knowledge Creation
- Goal-oriented exploration
- RAG-based content drafting
- Iterative document refinement
Adaptive Delivery
- Real-time content adaptation
- Personalized pacing
- Interactive feedback loops
Experimental Results
Key Performance Highlights:
Skill Identification
- High accuracy in goal-to-skill mapping
- Effective gap analysis
Learning Path Quality
- Optimal progression structure
- Strong learner engagement
Content Generation
- High relevance to goals
- Effective personalization
User Study Insights:
Learning Experience
- Clear learning guidance
- Improved goal achievement
System Design
- Intuitive interface
- High user satisfaction
Professional Impact
- Enhanced skill acquisition
- Efficient goal completion
Demo Video Presentation
BibTeX
@inproceedings{www2025genmentor,
title={LLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring System},
author={Tianfu Wang, Yi Zhan, Jianxun Lian, Zhengyu Hu, Nicholas Jing Yuan, Qi Zhang, Xing Xie, Hui Xiong},
booktitle={ACM Web Conference},
year={2025}
}