Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies

2025-02-04

AI Summary

Addressing the challenge of jointly optimizing prompt design and communication topology in multi-agent systems (MAS), this paper proposes MASS, an end-to-end automated framework. Its core innovation lies in (i) the first empirical identification of strong coupling between prompts and topology, and (ii) a staged, condition-dependent joint search paradigm enabled by design-space analysis—comprising block-level prompt fine-tuning, scalable topology search, and cross-stage conditional optimization. Evaluated on multiple complex tasks, MASS-optimized MAS consistently outperforms state-of-the-art methods. Furthermore, the study distills three generalizable, transferable design principles for MAS, offering both theoretical foundations and practical guidelines for MAS engineering.

Technology Category

• Multiagent Systems: Agent Communication
• Search and Optimization: Learning to Search
• Natural Language Processing: Prompt Engineering / Prompting

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Large language models, employed as multiple agents that interact and collaborate with each other, have excelled at solving complex tasks. The agents are programmed with prompts that declare their functionality, along with the topologies that orchestrate interactions across agents. Designing prompts and topologies for multi-agent systems (MAS) is inherently complex. To automate the entire design process, we first conduct an in-depth analysis of the design space aiming to understand the factors behind building effective MAS. We reveal that prompts together with topologies play critical roles in enabling more effective MAS design. Based on the insights, we propose Multi-Agent System Search (MASS), a MAS optimization framework that efficiently exploits the complex MAS design space by interleaving its optimization stages, from local to global, from prompts to topologies, over three stages: 1) block-level (local) prompt optimization; 2) workflow topology optimization; 3) workflow-level (global) prompt optimization, where each stage is conditioned on the iteratively optimized prompts/topologies from former stages. We show that MASS-optimized multi-agent systems outperform a spectrum of existing alternatives by a substantial margin. Based on the MASS-found systems, we finally propose design principles behind building effective multi-agent systems.

Problem

• Optimizing multi-agent system design
• Automating prompt and topology optimization
• Enhancing agent collaboration and task-solving

Innovation

• Multi-agent system optimization
• Prompt and topology design
• Automated design framework