Frontiers of Large Language Model-Based Agentic Systems - Construction, Efficacy and Safety

"The previous era was about information at your fingertips; I think of the AI era as expertise at your fingertips." - Satya Nadella, CNBC This tutorial explores Large Language Model (LLM)-based autonomous agents, addressing the lack of comprehensive guides on the topic. It systematically examines key components such as profiling, perception, memory, planning, and action, using an established taxonomy. The tutorial also extends the discussion to multi-agent frameworks, offering insights into collaborative intelligence. Additionally, it compares popular open-source frameworks for LLM-based agent development and discusses evaluation methodologies, focusing on efficiency and safety. The tutorial aims to catalyze dialogue and partnership among practitioners, propelling forward the integration of robust and effective LLM agent systems into the production environment.