题目：The rise of agentic knowledge management

时间：2025年11月24日（周一）16:00-18:00

地点：中科院数学院南楼N224

报告人：Quan Bai（University of Tasmania）

报告摘要：

The rapid expansion of organisational data and scientific outputs has rendered traditional knowledge management approaches increasingly insufficient. Advances in large AI models, particularly large language models (LLMs), multimodal systems, and agentic AI, now offer a transformative path forward. This talk examines how large AI can be harnessed to capture, organise, reason over, and disseminate knowledge at scale. I will introduce emerging architectures that integrate LLMs, retrieval-augmented generation (RAG), knowledge graphs, and autonomous agents to form dynamic, context-aware knowledge ecosystems. These systems can continuously ingest new information, adapt to evolving organisational needs, and generate tailored insights for diverse stakeholders. Drawing on recent research and practical case studies, the talk highlights the limitations of conventional knowledge management practices and the emergence of agentic, AI-driven knowledge management paradigms. Ultimately, the session outlines a pathway toward the next generation of intelligent, organisation-wide knowledge management powered by large AI.

报告人简介： 

Quan Bai received his PhD and MSc from the University of Wollongong, Australia. He is currently an Associate Professor at the University of Tasmania, where he leads a vibrant AI research group. A recognised expert in Agentic AI and machine learning, he is at the forefront of advancing next-generation intelligent systems. His research focuses on applying advanced AI methodologies to model and manage complex systems with highly interdependent components. He has published more than 180 peer-reviewed papers in leading journals and conferences and has attracted over AUD 4 million in research funding.