Event Details

Abstract: The rapid evolution of artificial intelligence has shifted focus from isolated, task-specific models to interconnected systems where multiple agents collaborate to solve complex, dynamic challenges. This presentation explores the progression from independent models to cooperative systems, focusing on LLMs as autonomous agents capable of learning not only from data but also through interaction with environments. We highlight how multi-agent debate frameworks enhance reasoning, factual accuracy, and decision-making by leveraging diverse perspectives, and how environment-grounded learning enables models to adapt through feedback and exploration. In doing so, we address critical challenges such as adversarial vulnerabilities, communication reliability, and long-term autonomy. By synthesizing insights from previous works, this talk outlines a roadmap for building trustworthy CAI systems that integrate cooperation with autonomous, environment-driven learning.

Speaker: Alfonso Amayuelas, UCSB

Zoom link
Zoom password: 2025

Host: DJ Ashok
POC: Maura Covaci

Speaker Bio

Alfonso Amayuelas is a PhD student in Computer Science in the Natural Language Processing Lab at the University of California, Santa Barbara, where he is supervised by Professor William Yang Wang. His research focuses on large language models, knowledge representation, reasoning, and multi-agent systems and autonomous learning. Alfonso holds an MSc in Data Science from EPFL and double Bachelor’s degree in Computer Science and Telecommunication Systems Engineering from the Autonomous University of Barcelona. He has experience in public and private research labs such as CERN, Aalto University, Oracle, JPMorgan or Morgan Stanley.