# On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents

**Source:** https://proceedings.mlr.press/v267/huang25ay.html  
**Authors or institution:** Jen-Tse Huang, Jiaxu Zhou, Tailin Jin, Xuhui Zhou, Zixi Chen, Wenxuan Wang, Youliang Yuan, Michael R. Lyu, Maarten Sap  
**Publication date:** 2025-07-13  
**Publication status:** ICML 2025 / PMLR 267  
**Evidence level:** Experimentally observed  
**Date last reviewed in UTC:** 2026-06-26T00:00:00Z

## Direct findings or source content

Group behavior and resilience depend on architecture and can differ from isolated-agent behavior.

## Cognivirus interpretation

For Cognivirus.com, this source is used to examine risk at the level of adaptive systems, component compositions, evaluator boundaries, and behavioral persistence. The site interpretation is narrower than the source when the source is experimental, and more explicitly qualified when the source is architectural or programmatic.

## Limits

Task structures and model choices bound the results. That any specific multi-agent production system is safe or unsafe by default.

## Source handling

This local file is an original summary and metadata record. It is not a copy of the source paper, report, or website. Copyrighted source material is not reproduced in full.