IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems

Yihuan Mao; Yipeng Kang; Peilun Li; Ning Zhang; Wei Xu; Chongjie Zhang

IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems

Yihuan Mao
, Yipeng Kang
, Peilun Li
, Ning Zhang
, Wei Xu
, Chongjie Zhang

Department of Computer Science & Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

As AI agents become integral to infrastructure, robust coordination and message synchronization are crucial. The Byzantine Generals Problem (BGP) models resilience in multi-agent systems (MAS) under adversarial conditions, handling scenarios with malicious agents-stemming from AI hallucinations or external attacks. Traditional BGP demands global consensus, which is often unnecessary and inefficient in practice. We introduce Imperfect BGP (IBGP), aligning with the local coordination patterns in MAS to address this gap, offering provable resilience against communication attacks and adaptability to changing environments, as validated by empirical results.

Original language	English
Title of host publication	Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025
Editors	Yevgeniy Vorobeychik, Sanmay Das, Ann Nowe
Publisher	International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages	2654-2656
Number of pages	3
ISBN (Electronic)	9798400714269
State	Published - 2025
Event	24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025 - Detroit, United States Duration: May 19 2025 → May 23 2025

Publication series

Name	Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
ISSN (Print)	1548-8403
ISSN (Electronic)	1558-2914

Conference

Conference	24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025
Country/Territory	United States
City	Detroit
Period	05/19/25 → 05/23/25

Keywords

Byzantine Generals Problem
Multi-agent Systems
Safety
Zero-shot Robustness

Cite this

Mao, Y., Kang, Y., Li, P., Zhang, N., Xu, W., & Zhang, C. (2025). IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems. In Y. Vorobeychik, S. Das, & A. Nowe (Eds.), Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025 (pp. 2654-2656). (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS). International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).

Mao, Yihuan ; Kang, Yipeng ; Li, Peilun et al. / IBGP : Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems. Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025. editor / Yevgeniy Vorobeychik ; Sanmay Das ; Ann Nowe. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2025. pp. 2654-2656 (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS).

@inproceedings{62eefacb57c84dd891bc3f2dcf4c7ab2,

title = "IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems",

abstract = "As AI agents become integral to infrastructure, robust coordination and message synchronization are crucial. The Byzantine Generals Problem (BGP) models resilience in multi-agent systems (MAS) under adversarial conditions, handling scenarios with malicious agents-stemming from AI hallucinations or external attacks. Traditional BGP demands global consensus, which is often unnecessary and inefficient in practice. We introduce Imperfect BGP (IBGP), aligning with the local coordination patterns in MAS to address this gap, offering provable resilience against communication attacks and adaptability to changing environments, as validated by empirical results.",

keywords = "Byzantine Generals Problem, Multi-agent Systems, Safety, Zero-shot Robustness",

author = "Yihuan Mao and Yipeng Kang and Peilun Li and Ning Zhang and Wei Xu and Chongjie Zhang",

note = "Publisher Copyright: {\textcopyright} 2025 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org).; 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025 ; Conference date: 19-05-2025 Through 23-05-2025",

year = "2025",

language = "English",

series = "Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS",

publisher = "International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)",

pages = "2654--2656",

editor = "Yevgeniy Vorobeychik and Sanmay Das and Ann Nowe",

booktitle = "Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025",

}

Mao, Y, Kang, Y, Li, P, Zhang, N, Xu, W & Zhang, C 2025, IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems. in Y Vorobeychik, S Das & A Nowe (eds), Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025. Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), pp. 2654-2656, 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025, Detroit, United States, 05/19/25.

IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems. / Mao, Yihuan; Kang, Yipeng; Li, Peilun et al.
Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025. ed. / Yevgeniy Vorobeychik; Sanmay Das; Ann Nowe. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2025. p. 2654-2656 (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - IBGP

T2 - 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025

AU - Mao, Yihuan

AU - Kang, Yipeng

AU - Li, Peilun

AU - Zhang, Ning

AU - Xu, Wei

AU - Zhang, Chongjie

PY - 2025

Y1 - 2025

N2 - As AI agents become integral to infrastructure, robust coordination and message synchronization are crucial. The Byzantine Generals Problem (BGP) models resilience in multi-agent systems (MAS) under adversarial conditions, handling scenarios with malicious agents-stemming from AI hallucinations or external attacks. Traditional BGP demands global consensus, which is often unnecessary and inefficient in practice. We introduce Imperfect BGP (IBGP), aligning with the local coordination patterns in MAS to address this gap, offering provable resilience against communication attacks and adaptability to changing environments, as validated by empirical results.

AB - As AI agents become integral to infrastructure, robust coordination and message synchronization are crucial. The Byzantine Generals Problem (BGP) models resilience in multi-agent systems (MAS) under adversarial conditions, handling scenarios with malicious agents-stemming from AI hallucinations or external attacks. Traditional BGP demands global consensus, which is often unnecessary and inefficient in practice. We introduce Imperfect BGP (IBGP), aligning with the local coordination patterns in MAS to address this gap, offering provable resilience against communication attacks and adaptability to changing environments, as validated by empirical results.

KW - Byzantine Generals Problem

KW - Multi-agent Systems

KW - Safety

KW - Zero-shot Robustness

UR - https://www.scopus.com/pages/publications/105009759849

M3 - Conference contribution

AN - SCOPUS:105009759849

T3 - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS

SP - 2654

EP - 2656

BT - Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025

A2 - Vorobeychik, Yevgeniy

A2 - Das, Sanmay

A2 - Nowe, Ann

PB - International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)

Y2 - 19 May 2025 through 23 May 2025

ER -

Mao Y, Kang Y, Li P, Zhang N, Xu W, Zhang C. IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems. In Vorobeychik Y, Das S, Nowe A, editors, Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS). 2025. p. 2654-2656. (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS).

IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems

Abstract

Publication series

Conference

Keywords

Other files and links

Fingerprint

Cite this