MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks

TL;DR

This paper introduces MASPOB, a bandit-based prompt optimization framework for multi-agent systems that efficiently improves performance by leveraging GNNs and coordinate ascent to address challenges like sample efficiency and complex search spaces.

Contribution

MASPOB is the first to combine bandit algorithms with GNNs and coordinate ascent for prompt optimization in multi-agent systems, enhancing efficiency and effectiveness.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Outperforms existing prompt optimization methods.

Reduces search complexity from exponential to linear.

Abstract

Large Language Models (LLMs) have achieved great success in many real-world applications, especially the one serving as the cognitive backbone of Multi-Agent Systems (MAS) to orchestrate complex workflows in practice. Since many deployment scenarios preclude MAS workflow modifications and its performance is highly sensitive to the input prompts, prompt optimization emerges as a more natural approach to improve its performance. However, real-world prompt optimization for MAS is impeded by three key challenges: (1) the need of sample efficiency due to prohibitive evaluation costs, (2) topology-induced coupling among prompts, and (3) the combinatorial explosion of the search space. To address these challenges, we introduce MASPOB (Multi-Agent System Prompt Optimization via Bandits), a novel sample-efficient framework based on bandits. By leveraging Upper Confidence Bound (UCB) to quantify uncertainty, the bandit framework balances exploration and exploitation, maximizing gains within a strictly limited budget. To handle topology-induced coupling, MASPOB integrates Graph Neural Networks (GNNs) to capture structural priors, learning topology-aware representations of prompt semantics. Furthermore, it employs coordinate ascent to decompose the optimization into univariate sub-problems, reducing search complexity from exponential to linear. Extensive experiments across diverse benchmarks demonstrate that MASPOB achieves state-of-the-art performance, consistently outperforming existing baselines.