Autonomy of LLM Agents: Current State and Future Prospects [ukr]
Talk presentation
We will analyze what actually works in the field of autonomous LLM agents, the existing limitations and their causes, research directions aimed at extending the duration of fully autonomous task execution, explore potential architectures of fully autonomous systems, economic autonomy of agents, and where we currently stand on the path toward achieving it.
Oles` Petriv
CTO & Co-founder of Reface
- CTO and Co-founder of Reface. Reface is a Ukrainian multi-product company whose apps are used by over 250 million people worldwide (Reface, Revive, Restyle, Letsy, Ink AI, Reshoot, BitePal, Honestly)
- He has been developing artificial neural network-based systems for 15 years in the fields of computer vision, NLP, and Generative AI
- He studied at the Kyiv-Mohyla Academy and has many years of experience creating products for video analytics and media quality enhancement for major Hollywood studios (Sony Pictures, Disney, Netflix, etc.) at VideoGorillas
- He is the author of several educational courses on machine learning fundamentals, holds patents for facial feature modification technologies in video, and has developed analytical systems for news analysis, automation technologies for analytics in the retail sector, and elevation map modeling systems based on satellite imagery. He is actively involved in the development of agent-based systems powered by multimodal language models
- He is a member of the board of directors of AI HOUSE, the largest AI community in Ukraine