AI RESEARCH
OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration
arXiv CS.AI
•
ArXi:2505.11765v3 Announce Type: replace-cross Agents powered by advanced large language models (LLMs) have nstrated impressive capabilities across diverse complex applications. Recently, Multi-Agent Systems (MAS), wherein multiple agents collaborate and communicate with each other, have exhibited enhanced capabilities in complex tasks, such as high-quality code generation and arithmetic reasoning. However, the development of such systems often relies on handcrafted methods, and the literature on systematic design and optimization of LLM-based MAS remains limited. In this work, we