# Byzantine-Robust Decentralized Coordination of LLM Agents

arXiv: https://arxiv.org/abs/2507.14928 · HTML: https://mlsanity.com/paper/2507.14928/

## Key facts

- Cited by 14 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 19 of its 35 references that are in the map.
- First posted on arXiv 20 Jul 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, 19 of 19)

- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [The Hidden Vulnerability of Distributed Learning in Byzantium](https://mlsanity.com/paper/1802.07927/) (2018)
- [More Agents Is All You Need](https://mlsanity.com/paper/2402.05120/) (2024)
- [Human-like Summarization Evaluation with ChatGPT](https://mlsanity.com/paper/2304.02554/) (2023)
- [Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs](https://mlsanity.com/paper/2311.17371/) (2023)
- [Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate](https://mlsanity.com/paper/2305.11595/) (2023)
- [A Survey on Trustworthy LLM Agents: Threats and Countermeasures](https://mlsanity.com/paper/2503.09648/) (2025)
- [Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2502.14321/) (2025)
- [Sequential Diagnosis with Language Models](https://mlsanity.com/paper/2506.22405/) (2025)
- [DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models](https://mlsanity.com/paper/2410.07331/) (2024)
- [A Survey of Recent Backdoor Attacks and Defenses in Large Language Models](https://mlsanity.com/paper/2406.06852/) (2024)
- [When One LLM Drools, Multi-LLM Collaboration Rules](https://mlsanity.com/paper/2502.04506/) (2025)
- [Blockchain Large Language Models](https://mlsanity.com/paper/2304.12749/) (2023)
- [Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding Tasks](https://mlsanity.com/paper/2503.12029/) (2025)
- [A Weighted Byzantine Fault Tolerance Consensus Driven Trusted Multiple Large Language Models Network](https://mlsanity.com/paper/2505.05103/) (2025)
- [Narwhal and Tusk: A DAG-based Mempool and Efficient BFT Consensus](https://mlsanity.com/paper/2105.11827/) (2021)

## Built on by (most cited first, 14 of 14)

- [A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework](https://mlsanity.com/paper/2604.23338/) (2026)
- [Robust Multi-Agent LLMs under Byzantine Faults](https://mlsanity.com/paper/2605.09076/) (2026)
- [Can AI Agents Agree?](https://mlsanity.com/paper/2603.01213/) (2026)
- [Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs](https://mlsanity.com/paper/2605.06320/) (2026)
- [Blockchain Empowered Trustworthy Agent Networks: Foundations, Taxonomy, and Future Directions](https://mlsanity.com/paper/2608.04626/) (2026)
- [SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems](https://mlsanity.com/paper/2609.00595/) (2026)
- [When AI Agents Disagree Like Humans: Reasoning Trace Analysis for Human-AI Collaborative Moderation](https://mlsanity.com/paper/2604.03796/) (2026)
- [Engineering Trustworthy Agentic AI for Critical Systems](https://mlsanity.com/paper/2607.18548/) (2026)
- [PRIMUS: Identity, Governance, and Verification for Multi-Agent Federations](https://mlsanity.com/paper/2609.07910/) (2026)
- [Agentic Societies Need a Social Harness](https://mlsanity.com/paper/2609.17527/) (2026)
- [MeshHeal: Two-Timescale Self-Healing for Gray Failures in Decentralized LLM Agent Networks](https://mlsanity.com/paper/2609.29015/) (2026)
- [Reinforcement Learning of Communication in a Mesh of Small Language Models](https://mlsanity.com/paper/2609.30578/) (2026)
- [Be Careful Who You Trust: Coordination Dynamics under Corrupted Communication in LLM Multi-Agent Games](https://mlsanity.com/paper/2609.31704/) (2026)
- [Re-derivability Decides What a Staged Agent Pipeline Recovers After an Upstream Fault](https://mlsanity.com/paper/2609.32802/) (2026)

## Abstract (arXiv)

Collaboration among multiple large language model (LLM) agents is a promising approach to overcome inherent limitations of single-agent systems, such as hallucinations and single points of failure. As LLM agents are increasingly deployed on open blockchain platforms, multi-agent systems capable of tolerating malicious (Byzantine) agents have become essential. Recent Byzantine-robust multi-agent systems typically rely on leader-driven coordination, which suffers from two major drawbacks. First, they are inherently vulnerable to targeted attacks against the leader. If consecutive leaders behave maliciously, the system repeatedly fails to achieve consensus, forcing new consensus rounds, which is particularly costly given the high latency of LLM invocations. Second, an underperforming proposal from the leader can be accepted as the final answer even when higher-quality alternatives are available, as existing methods finalize the leader's proposal once it receives a quorum of votes. To address these issues, we propose DecentLLMs, a novel decentralized consensus approach for multi-agent LLM systems, where worker agents generate answers concurrently and evaluator agents independently score and rank these answers to select the best available one. This decentralized architecture enables faster consensus despite the presence of Byzantine agents and consistently selects higher-quality answers through Byzantine-robust aggregation techniques. Experimental results demonstrate that DecentLLMs effectively tolerates Byzantine agents and significantly improves the quality of selected answers.