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

TL;DR
This paper introduces IBGP, a refined Byzantine Generals Problem model tailored for multi-agent systems, enhancing robustness against adversarial attacks and hallucinations in large language model agents through a consensus protocol framework.
Contribution
The paper proposes IBGP, a novel variant of BGP for local coordination in MAS, with a resilient consensus protocol validated by empirical case studies.
Findings
Proposed IBGP improves robustness against communication attacks.
Framework demonstrates adaptability in dynamic environments.
Empirical case study confirms practical effectiveness.
Abstract
As large language model (LLM) agents increasingly integrate into our infrastructure, their robust coordination and message synchronization become vital. The Byzantine Generals Problem (BGP) is a critical model for constructing resilient multi-agent systems (MAS) under adversarial attacks. It describes a scenario where malicious agents with unknown identities exist in the system-situations that, in our context, could result from LLM agents' hallucinations or external attacks. In BGP, the objective of the entire system is to reach a consensus on the action to be taken. Traditional BGP requires global consensus among all agents; however, in practical scenarios, global consensus is not always necessary and can even be inefficient. Therefore, there is a pressing need to explore a refined version of BGP that aligns with the local coordination patterns observed in MAS. We refer to this refined…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDistributed Control Multi-Agent Systems · Mobile Agent-Based Network Management · Logic, Reasoning, and Knowledge
