Title: Concordia: Advancing the Cooperative Intelligence of Language Agents

Speaker: Dr. Minsuk Chang @ Google Deepmind

Time : 09:00 ~ 10:00, Mar 27th, 2025

Location: Online

• In-person: X

• Online: https://skku-edu.zoom.us/j/87833822632?pwd=bdbsuNThKskPRqV5uucpZTNaS4EwTU.1 

  • Meeting ID: 878 3382 2632

  • Passcode: 667064

Language: English speech & English slides

Abstract: 

This talk introduces Concordia, a framework for developing and evaluating cooperative intelligence in agents built with Large Language Models (LLMs). Building upon the rich history of Agent-Based Modeling (ABM), Concordia empowers researchers to construct Generative Agent-Based Models (GABMs), where LLM-powered agents interact with each other and their environment through natural language. Concordia facilitates the creation of complex, language-mediated simulations of diverse scenarios, from physical worlds to digital environments involving apps and services. By enabling the study of cooperation among LLM agents in challenging scenarios, such as those involving competing interests and potential miscommunication, Concordia aims to advance research on cooperative and social intelligence. This research is critical as we witness the rapid growth of LMs and anticipate the increasing prevalence of personalized agents in our lives. The ability of these agents to effectively cooperate with one another and with humans will be crucial for their successful and beneficial integration into society.

Bio:

Minsuk Chang is a Research Scientist at Google DeepMind, where his work centers on the acquisition of skills and knowledge in both artificial and natural agents.  His research investigates the dynamics of learning processes, seeking to elucidate how agents effectively gather information, adapt to novel environments, and expand their behavioral repertoires.  Prior to joining Google DeepMind, he worked on HyperClova, Naver AI Lab's large language model initiative. He holds a PhD in Computer Science from KAIST.