analiza aiqbench
OMAC introduces a systematic framework for optimizing Large Language Model-based Multi-Agent Systems by addressing five key dimensions of agent functionality and collaboration structure. By automating the optimization process through its Semantic Initializer and Contrastive Comparator actors, this approach moves beyond handcrafted methods to achieve superior performance across diverse complex tasks like code generation and arithmetic reasoning. This work represents a significant advancement in Machine Learning research for scaling collaborative AI agents efficiently.
OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration
arXiv:2505.11765v5 Announce Type: replace-cross Abstract: Agents powered by advanced large language models (LLMs) have demonstrated 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 introduce \textbf{OMAC}, a general framework designed for holistic optimization of LLM-based MAS. Specifically, we identify five key optimization dimensions for MAS, encompassing both agent functionality and collaboration structure. Building upon these dimensions, we first propose a general algorithm, utilizing two actors termed the Semantic Initializer and the Contrastive Comparator, to optimize any single dimension. Then, we present an algorithm for joint optimization across multiple dimensions. Extensive experiments demonstrate the superior performance of OMAC on diverse tasks against recent approaches.
Abstract:Agents powered by advanced large language models (LLMs) have demonstrated 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 introduce \textbf{OMAC}, a general framework designed for holistic optimization of LLM-based MAS. Specifically, we identify five key optimization dimensions for MAS, encompassing both agent functionality and collaboration structure. Building upon these dimensions, we first propose a general algorithm, utilizing two actors termed the Semantic Initializer and the Contrastive Comparator, to optimize any single dimension. Then, we present an algorithm for joint optimization across multiple dimensions. Extensive experiments demonstrate the superior performance of OMAC on diverse tasks against recent approaches.
Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2505.11765 [cs.MA]
(or arXiv:2505.11765v5 [cs.MA] for this version)
Text integral sub licența deschisă a publicației · 168 cuvinte
Subiecte conexe
Learning Agent-based Model Predictive Control for Holistic Vehicle Performance
arXiv · 11 sept. 2026
The Machines that Make the Machines
NVIDIA · 7 oct. 2026
Intelligence is Free, Now What? <br> Data Systems for, of, and by Agents
BAIR Blog · 7 iul. 2026
News
Quantum Computing Report · 7 iun. 2026