Assessing and Enhancing the Robustness of LLM-based Multi-Agent Systems Through Chaos Engineering

TL;DR

This paper applies chaos engineering principles to improve the robustness and reliability of Large Language Model-Based Multi-Agent Systems in real-world scenarios, addressing vulnerabilities like hallucinations and communication failures.

Contribution

It introduces a novel chaos engineering framework specifically designed for LLM-MAS to proactively identify vulnerabilities and enhance system resilience.

Findings

Identified key vulnerabilities in LLM-MAS such as hallucinations and agent failures.

Demonstrated the effectiveness of chaos engineering in improving system robustness.

Provided guidelines for deploying resilient LLM-MAS in production environments.

Abstract

This study explores the application of chaos engineering to enhance the robustness of Large Language Model-Based Multi-Agent Systems (LLM-MAS) in production-like environments under real-world conditions. LLM-MAS can potentially improve a wide range of tasks, from answering questions and generating content to automating customer support and improving decision-making processes. However, LLM-MAS in production or preproduction environments can be vulnerable to emergent errors or disruptions, such as hallucinations, agent failures, and agent communication failures. This study proposes a chaos engineering framework to proactively identify such vulnerabilities in LLM-MAS, assess and build resilience against them, and ensure reliable performance in critical applications.