OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration

arXiv:2505.11765v3 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 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 code generation, arithmetic reasoning, and general reasoning tasks against state-of-the-art approaches.

Related

• PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation via Multi-Agent LLMs
• AMA: Adaptive Memory via Multi-Agent Collaboration
• Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decomposition
• AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations
• EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale

Source: arXiv cs.AI | 2026-04-22