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

arXiv: https://arxiv.org/abs/2410.16237 · HTML: https://mlsanity.com/paper/2410.16237/

## Key facts

- No citing papers in the map yet (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 7 of its 26 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## 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, 7 of 7)

- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1905.05408/) (2019)
- [Deep Coordination Graphs](https://mlsanity.com/paper/1910.00091/) (2019)
- [Learning Nearly Decomposable Value Functions Via Communication Minimization](https://mlsanity.com/paper/1910.05366/) (2019)
- [Incorporating Pragmatic Reasoning Communication into Emergent Language](https://mlsanity.com/paper/2006.04109/) (2020)
- [Robust Communicative Multi-Agent Reinforcement Learning with Active Defense](https://mlsanity.com/paper/2312.11545/) (2023)
- [Animating the Past: Reconstruct Trilobite via Video Generation](https://mlsanity.com/paper/2410.14715/) (2024)

## Abstract (arXiv)

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 version as Imperfect BGP (IBGP) in our research, aiming to address this discrepancy. To tackle this issue, we propose a framework that leverages consensus protocols within general MAS settings, providing provable resilience against communication attacks and adaptability to changing environments, as validated by empirical results. Additionally, we present a case study in a sensor network environment to illustrate the practical application of our protocol.