LLM Agents for Real-World Applications. The case of Financial Analysis and Training assistants in VR

George Fatouros is an AI Engineer, Researcher, and Chief Technology Officer at Alpha Tensor Technologies. Soon to complete his Ph.D. in Applied Artificial Intelligence from University of Piraeus, George also holds an MSc in Data Science and a Diploma in Economics. With a specialization in machine learning, data analytics, and software development, George has led technical activities in multiple R&D projects and has made significant contributions to the field, recognized in prestigious journals and conferences. As CTO and co-founder of Alpha Tensor Technologies, George drives the technological strategy and development, focusing on practical, cutting-edge applications of Generative AI in financial markets and analysis.ance is undeniably superior to previous approaches. With this success, the critical questions now are: What are the limitations of current large-scale learning? What frontiers remain? And what are the implications of these developments?

Ακολουθεί σύντομη περιγραφή

This presentation delves into the transformative capabilities of Large Language Models (LLMs), exploring their foundational principles and real-world applications. It discusses the key milestones in Natural Language Processing (NLP), explaining the inner workings of LLMs and approaches for bootstrapping them, such as Retrieval-Augmented Generation (RAG) and architectures for building LLM Agents. The focus then shifts to practical implementations, spotlighting MarketSenseAI and MarketSenseGPT—innovative tools leveraging GPT-4 for explainable stock analysis and selection. These systems integrate diverse financial data sources, including news, market trends, fundamentals, and macroeconomic indicators, to emulate expert-level decision-making. Additional use cases will be discussed including LLM assisted industrial training in VR and multi-agent LLM systems for collaborative problem-solving