G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Guibin, Yue, Yanwei, Sun, Xiangguo, Wan, Guancheng, Yu, Miao, Fang, Junfeng, Wang, Kun, Chen, Tianlong, Cheng, Dawei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910816209469440
author Zhang, Guibin
Yue, Yanwei
Sun, Xiangguo
Wan, Guancheng
Yu, Miao
Fang, Junfeng
Wang, Kun
Chen, Tianlong
Cheng, Dawei
author_facet Zhang, Guibin
Yue, Yanwei
Sun, Xiangguo
Wan, Guancheng
Yu, Miao
Fang, Junfeng
Wang, Kun
Chen, Tianlong
Cheng, Dawei
contents Recent advancements in large language model (LLM)-based agents have demonstrated that collective intelligence can significantly surpass the capabilities of individual agents, primarily due to well-crafted inter-agent communication topologies. Despite the diverse and high-performing designs available, practitioners often face confusion when selecting the most effective pipeline for their specific task: \textit{Which topology is the best choice for my task, avoiding unnecessary communication token overhead while ensuring high-quality solution?} In response to this dilemma, we introduce G-Designer, an adaptive, efficient, and robust solution for multi-agent deployment, which dynamically designs task-aware, customized communication topologies. Specifically, G-Designer models the multi-agent system as a multi-agent network, leveraging a variational graph auto-encoder to encode both the nodes (agents) and a task-specific virtual node, and decodes a task-adaptive and high-performing communication topology. Extensive experiments on six benchmarks showcase that G-Designer is: \textbf{(1) high-performing}, achieving superior results on MMLU with accuracy at $84.50\%$ and on HumanEval with pass@1 at $89.90\%$; \textbf{(2) task-adaptive}, architecting communication protocols tailored to task difficulty, reducing token consumption by up to $95.33\%$ on HumanEval; and \textbf{(3) adversarially robust}, defending against agent adversarial attacks with merely $0.3\%$ accuracy drop.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11782
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks
Zhang, Guibin
Yue, Yanwei
Sun, Xiangguo
Wan, Guancheng
Yu, Miao
Fang, Junfeng
Wang, Kun
Chen, Tianlong
Cheng, Dawei
Multiagent Systems
Machine Learning
Recent advancements in large language model (LLM)-based agents have demonstrated that collective intelligence can significantly surpass the capabilities of individual agents, primarily due to well-crafted inter-agent communication topologies. Despite the diverse and high-performing designs available, practitioners often face confusion when selecting the most effective pipeline for their specific task: \textit{Which topology is the best choice for my task, avoiding unnecessary communication token overhead while ensuring high-quality solution?} In response to this dilemma, we introduce G-Designer, an adaptive, efficient, and robust solution for multi-agent deployment, which dynamically designs task-aware, customized communication topologies. Specifically, G-Designer models the multi-agent system as a multi-agent network, leveraging a variational graph auto-encoder to encode both the nodes (agents) and a task-specific virtual node, and decodes a task-adaptive and high-performing communication topology. Extensive experiments on six benchmarks showcase that G-Designer is: \textbf{(1) high-performing}, achieving superior results on MMLU with accuracy at $84.50\%$ and on HumanEval with pass@1 at $89.90\%$; \textbf{(2) task-adaptive}, architecting communication protocols tailored to task difficulty, reducing token consumption by up to $95.33\%$ on HumanEval; and \textbf{(3) adversarially robust}, defending against agent adversarial attacks with merely $0.3\%$ accuracy drop.
title G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks
topic Multiagent Systems
Machine Learning
url https://arxiv.org/abs/2410.11782