Annual Conference of KIPS (한국정보처리학회:학술대회논문집)

  • 2025.05a
  • /
  • Pages.747-748
  • /
  • 2025
  • /
  • 2005-0011(pISSN)
  • /
  • 2671-7298(eISSN)
Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

A Comprehensive Survey on Multi-Agent Systems Recent Advances and Limitations

Multi-Agent 시스템에 관한 종합적 고찰: 최신 연구 동향과 한계점

  • Na-Yeon Kim (Dept. of Convergence Security Engineering, Sungshin Women's University) ;
  • Min-Ji Kim (Dept. of Convergence Security Engineering, Sungshin Women's University) ;
  • Younghan Lee (Dept. of Convergence Security Engineering, Sungshin Women's University)
  • 김나연 (성신여자대학교 융합보안공학과) ;
  • 김민지 (성신여자대학교 융합보안공학과) ;
  • 이영한 (성신여자대학교 융합보안공학과)
  • Published : 2025.05.29
Download PDF
⟨ Previous Next ⟩

Abstract

Recent advancements in Large Language Models (LLMs) have led to the active development of multi-agent systems (MAS) for collaborative problem-solving. This paper provides a comprehensive review of MAS structures and applications, focusing on two recent frameworks-CodeAgent and MetaGPT-that leverage LLMs in complex software engineering tasks. Through detailed examination of their design and workflows, we identify the strengths and limitations of each system and propose future directions to improve the adaptability and scalability of MAS frameworks while addressing their reliability challenges.

Keywords

Acknowledgement

This research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ICAN(ICT Challenge and Advanced Network of HRD) program(No. IITP-2022-RS-2022-00156310) supervised by the IITP(Institute of Information & Communications Technology Planning & Evaluation)