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

arXiv: https://arxiv.org/abs/2505.03096 · HTML: https://mlsanity.com/paper/2505.03096/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 6 May 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Improving Alignment and Robustness with Circuit Breakers](https://mlsanity.com/paper/2406.04313/) (2024)
- [Synchromesh: Reliable code generation from pre-trained language models](https://mlsanity.com/paper/2201.11227/) (2022)
- [Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2410.02506/) (2024)
- [LLM Multi-Agent Systems: Challenges and Open Problems](https://mlsanity.com/paper/2402.03578/) (2024)
- [Examining Zero-Shot Vulnerability Repair with Large Language Models](https://mlsanity.com/paper/2112.02125/) (2021)
- [Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation](https://mlsanity.com/paper/2308.10335/) (2023)
- [Robust LLM safeguarding via refusal feature adversarial training](https://mlsanity.com/paper/2409.20089/) (2024)
- [A Survey on Evaluating Large Language Models in Code Generation Tasks](https://mlsanity.com/paper/2408.16498/) (2024)
- [Exploring Autonomous Agents through the Lens of Large Language Models: A Review](https://mlsanity.com/paper/2404.04442/) (2024)
- [NetSafe: Exploring the Topological Safety of Multi-agent Networks](https://mlsanity.com/paper/2410.15686/) (2024)
- [Why Solving Multi-agent Path Finding with Large Language Model has not Succeeded Yet](https://mlsanity.com/paper/2401.03630/) (2024)
- [Chaos Engineering](https://mlsanity.com/paper/1702.05843/) (2017)
- [System for systematic literature review using multiple AI agents: Concept and an empirical evaluation](https://mlsanity.com/paper/2403.08399/) (2024)
- [Data Quality Certification using ISO/IEC 25012: Industrial Experiences](https://mlsanity.com/paper/2102.11527/) (2021)
- [A Chaos Engineering System for Live Analysis and Falsification of Exception-handling in the JVM](https://mlsanity.com/paper/1805.05246/) (2018)
- [Chaos Engineering of Ethereum Blockchain Clients](https://mlsanity.com/paper/2111.00221/) (2021)

## Built on by (most cited first, 6 of 6)

- [A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures](https://mlsanity.com/paper/2506.19676/) (2025)
- [Hiding in the AI Traffic: Abusing MCP for LLM-Powered Agentic Red Teaming](https://mlsanity.com/paper/2511.15998/) (2025)
- [Extending the OWASP Multi-Agentic System Threat Modeling Guide: Insights from Multi-Agent Security Research](https://mlsanity.com/paper/2508.09815/) (2025)
- [StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems](https://mlsanity.com/paper/2606.03467/) (2026)
- [Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents](https://mlsanity.com/paper/2511.10687/) (2025)
- [Code Broker: A Multi-Agent System for Automated Code Quality Assessment](https://mlsanity.com/paper/2604.23088/) (2026)

## Abstract (arXiv)

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.