Newest papers

The End of Consensus Research?

Clément Burgelin, Rachid Guerraoui, Zicong Hong, Yinan Hu, Anne-Marie Kermarrec, Rafael Pires, Rasmus Moorits Veski, Martijn de Vos · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.30114 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

在分布式计算和状态框架复制(SMR)的核心上,共识代理在分布式计算中是一个基本问题。尽管有几十年的活跃人类研究,对问题的有效低延迟解决方案的发现仍然是开放的,因为它需要结合协议知识,正确性推理,实施和实验性评估。我们报告了人工智能如何帮助我们发现A-greement,一个新的共识协议,用于地理复制状态机器,这显著超过了最先进的解决方案。在六个特定部署中,它需要结合协议知识,正确性推理,实施和实验性评估。A-greement降低了地理分布式关键值存储的平均延迟,在最快的基线上发现A-greement,分别是12%和33%的地理重复制状态工作负载,并且符合人类定义模块

Machine translation (Meta M2M100); the English original follows.

Abstract

Consensus is a fundamental problem in distributed computing and at the core of state machine replication (SMR). Despite decades of active human research, discovering practical low-latency solutions to the problem is still open, as it requires combining protocol knowledge, correctness reasoning, implementation, and experimental evaluation. We report on how AI helped us discover A-greement, a new consensus protocol for geo-replicated state machines that significantly outperforms state-of-the-art solutions. Averaged across six deployments with 5 or 9 replicas, A-greement reduces the mean latency of a geo-distributed key-value store over the fastest baseline by 12.2% and 33.3% on write-heavy and read-heavy workloads, respectively, and matches the fastest baseline on read-only workloads. A-greement combines lease-authorized local reads, direct client learning for leader-ordered writes, and a fast fixed-quorum per-key write path, selected according to network topology and workload. At the heart of our discovery lies AI-greement, an agent harness for the "autonomous" discovery, implementation, experimentation, and verification of candidate protocols. AI-greement integrates (1) a concept-oriented protocol knowledge base, (2) a modular implementation skeleton, and (3) a Lean-based verification framework with reusable safety definitions, reference specifications, and proofs. AI-greement is of independent interest: its Lean formalization uncovers several previously unreported vulnerabilities in existing consensus protocols, and it provides guidelines on how domain-specific harnesses can turn general-purpose coding agents into effective tools for (distributed) computing research. Yet we argue that human consensus experts remain essential before, during, and after the search: agents reshape the researcher's role rather than end consensus research.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Correctness, Computer science, Protocol (science), Consensus algorithm, Modular design, Distributed computing

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange