LLM- and RAG-Enabled Multi-Agent AI Systems
Interaction and knowledge enhancement with tool-using agents
LLM-Enabled Multi-Agent SystemsOverview
LLM- and RAG-Enabled Multi-Agent AI Systems combine large language models with retrieval-augmented generation to create intelligent agents that can interact, reason, and assist with complex tasks.
Key Features
- Large Language Models: Advanced natural language understanding and generation
- Retrieval-Augmented Generation: Knowledge-enhanced responses
- Multi-Agent Coordination: Collaborative problem-solving
- Tool Integration: Seamless interaction with external systems
Applications
- Enterprise: Knowledge assistants for organizational information
- Research: Copilots for scientific discovery and literature review
- Business: Workflow automation and process optimization
- Healthcare: Clinician-facing Q&A and decision support
Deliverables
- AI System for Suicide Assessment and Prevention
- SBIRT Virtual Counselor
- SOBER (Systematic Orchestration of Behavioral Recovery)
Innovation
These systems represent the next generation of AI assistants, capable of understanding context, accessing relevant knowledge, and providing actionable insights.
Lu Wang
Assistant Professor of Biomedical Engineering
My research interests are developing and applying Machine Learning, Data Mining and Statistical methods (e.g., Multi-task Learning, Survival Analysis, Clustering, Risk Factor Analysis and Causal Discovery) on various data including gene expression, electronic health/medical records, and DNA sequencing reads for both cognitive disorders (e.g., delirium, Alzheimer’s disease, dementia, major depressive disorder) and chronic diseases (e.g., cancer, obesity, hypertension). Inspired by the human factors approach, she also designs and develops Human-Centered Artificial Intelligence tools for users to integrate, visualize, analyze, and interpret health data in order to improve the interoperability and accessibility of AI-assisted healthcare decision support.