LLM Agents: From Language to Action
By Prof. Chao HUANG, Assistant Professor, School of Computing & Data Science, Institute of Data Science, HKU
Note: Both onsite and online registration can be done through the same link
Abstract
In recent years, the emergence of Large Language Models (LLMs) has revolutionized artificial intelligence, enabling machines to understand and generate human-like text with unprecedented capabilities. However, the true potential of LLMs extends far beyond language generation—when combined with intelligent agents, they bridge the critical gap between understanding and action. This seminar will explore the transformative synergy between LLMs and Autonomous Agents. Prof. Huang will investigate cutting-edge research, including advancements driven by LLM Agents that enable systems to interpret natural language instructions and execute complex tasks, such as programming, web search, information analysis, and comprehensive report generation, in real-world dynamic environments. Tools will be demonstrated during the session:
- Auto-Deep-Research: https://github.com/HKUDS/Auto-Deep-Research
- AutoAgent: https://github.com/HKUDS/AutoAgent
After completing this session, participants will be able to
- Understand the fundamental capabilities of Large Language Models (LLMs) and how they extend beyond basic text generation to enable complex reasoning and task execution.
- Identify and analyze the synergistic relationship between LLMs and Autonomous Agents, and how this combination creates systems capable of bridging understanding with real-world actions.
- Evaluate cutting-edge applications of LLM Agents across diverse domains, including programming, web search, information analysis, and report generation in dynamic environments.
About the Speaker
Prof. Chao HUANG
Assistant Professor, School of Computing & Data Science, Institute of Data Science, HKU
Prof. HUANG is currently an Assistant Professor & PhD supervisor in the Department of Computer Science and Institute of Data Science at The University of Hong Kong. His research interests span several crucial areas of artificial intelligence, including Large Language Model (LLM), Intelligent Agents, Graph Learning, Recommender Systems, and Smart Cities. His research contributions have received widespread recognition in academia, with his papers being selected as influential papers at premier conferences including KDD (2019/2023/2024), WWW (2023/2024), and SIGIR (2021/2022/2023/2024). Additionally, his work has been honored with best paper awards or nominations at major conferences, including ACM MM 2024, WWW 2023, WSDM 2022, and WWW 2019. His academic publications have garnered over 9,600 citations. For three consecutive years from 2022 to 2024, Prof. Huang has been recognized among the World’s Top 2% Scientists as published by Stanford University. Additionally, Dr. Huang’s lab has also developed several widely recognized open-source projects, such as LightRAG, AutoAgent, AI-Researcher, MiniRAG, GraphGPT, VideoRAG, etc. These projects have collectively garnered over 23,000 stars on open-source Github platforms. In recognition of his outstanding contributions to artificial intelligence, Dr. Huang was awarded the “Bright Star Award” at the 2024 World Artificial Intelligence Conference (WAIC) and received the “2024 Frontier Science Award in Theoretical Computer Science and Information Science.”
About the Speaker
