Concordia: Advancing the Cooperative Intelligence of Language Agents
- 신청기간
- 2025.02.07. 00:00 ~ 2025.02.18. 17:00
- 활동기간
- 2025.02.19. ~ 2025.02.19.
- 선발확인일시
- 2025.02.19 10:00 이후
- 선정방법
- 선착순선발
- 수료인증서
- 발급가능
- 신청대상(소속)
- 서울대학교
- 신청신분
- 전체
신청대상 상세정보
- 학적
- 국적
- 내국인+외국인
- 과정
- 학년
- 구분
- 전체
- 재직
- 재직
프로그램 기본정보
- 운영년도
- 2024
- 운영학기
- 겨울학기
- 운영부서
- 사회과학대학
- 비교과 시스템 역량
- 학부대학 핵심역량
- 키워드
- #MinsukChang#Google#Concordia#LLMs#ABM#LLM#대규모언어모델#Deepmind#장민석
- 문의전화
- 02-880-2298
- 문의메일
- kimjoo15@snu.ac.kr
- 장애학생 지원사항
- 첨부파일
프로그램 주요내용
Google Deepmind에서 Research Scientist로 활동하고 계신 장민석 박사님을 모시고 진행하는 이번 워크숍에서는 에이전트의 협력 지능을 개발하고 평가하기 위해 대규모 언어 모델(LLM)에 기반하여 구축된 프레임워크인 Concordia에 대해 소개합니다.
- 강의 개요
: 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. Within these simulations, agents employ a flexible component system to guide their actions, seamlessly integrating LLM calls with associative memory retrieval. A key feature of Concordia is the "Game Master," inspired by tabletop role-playing games, which simulates the environment, translates agent actions into appropriate implementations, and ensures the realism of interactions. 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.
- 강연자 소개
: Minsuk Chang is interested in our and other agents’ (in)ability to acquire new skills/knowledge through interaction. He builds and studies the dynamics of learning processes, seeking to understand how agents can effectively gather information, adapt to new situations, and expand their repertoire of behaviors.
- 강의언어: 한국어
강좌 정보
| 출석관리 | Y | 진행속성 | 1회 |
|---|
|
[1]
회차 | 강좌명 | Concordia: Advancing the Cooperative Intelligence of Language Agents |
|---|---|---|
| 교육(활동)장소 | 223동 우석경제관 107호 | |
| 교육(활동)기간 | 2025.02.19. 14:00 ~ 2025.02.19. 16:00 | |
| 강사(진행자) | Minsuk Chang (Research Scientist, Google Deepmind) | |
| 첨부파일 | ||
| 과제(자료)제출 | 미제출 |