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

TL;DR

This paper introduces MASS, a framework for optimizing prompts and topologies in multi-agent systems, significantly improving their effectiveness through a staged, iterative design process.

Contribution

The paper presents MASS, a novel multi-stage optimization framework that automates the design of prompts and topologies for multi-agent systems, outperforming existing methods.

Findings

MASS-optimized systems outperform existing alternatives.

Prompts and topologies are critical for effective multi-agent system design.

The staged optimization approach effectively explores the complex design space.

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.