2025-05-27 –, Stage One
Generative AI and LLM applications have recently started to advance beyond simple question-answering and basic text summarization tasks. The next frontier in NLP lies in harnessing these technologies to create autonomous agents - systems capable of reasoning, planning, and executing complex sequences of actions with minimal human intervention. This talk will explore the principles and challenges of designing such agents, focusing on how LLMs can function as core components for decision-making and goal-oriented planning. We will review strategies for integrating LLMs with external tools, APIs, and feedback loops, with the purpose of enabling adaptive behaviour in dynamic environments. We will also highlight real-world applications, from task orchestration and code generation to multi-agent collaborative workflows. Whether you're an AI enthusiast, developer, or researcher, this session will provide a roadmap for navigating this exciting domain of truly intelligent AI-driven automation.
Catalin Hanga (PhD) is a Data Scientist, currently working at the Open Innovation AI Lab of Iveco Group in Switzerland. His main professional focus is on research and development of advanced machine learning algorithms for solving technical problems in the automotive industry. His recent projects include designing a documentation search chatbot based on Retrieval Augmented Generation, as well as implementing autonomous LLM agents with function calling and tool usage. Prior to this, he briefly worked in a similar role for a startup in the insurtech industry. He has obtained a PhD in Mathematics from the University of York, UK, and holds an M.Sc. in Physics from the University of Bucharest, Romania. During his M.Sc. studies, he also worked as a researcher at CERN in Geneva, Switzerland, analysing experimental data collected by the detectors of the Large Hadron Collider. He is regularly giving public talks on technical topics at various Data Science and AI conferences.