arXiv cs.AI· Cl\'ement Burgelin, Rachid Guerraoui, Zicong Hong, Yinan Hu, Anne-Marie Kermarrec, Rafael Pires, Rasmus Moorits Veski, Martijn de Vos·· 13 小时前AI 评分58
AI 智能体发现新共识协议 A-greement，写密集负载延迟降低 12.2%
The End of Consensus Research?
AI 导读
论文报告 AI 帮助发现新共识协议 A-greement，在 5 或 9 副本的六种部署中，地理分布式键值存储的写密集和读密集负载平均延迟分别比最快基线降低 12.2% 和 33.3%，只读负载与最快基线持平。
正文 · 原文
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.
| Comments: | 39 pages |
| Subjects: | Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI) |
| ACM classes: | C.2.4 |
| Cite as: | arXiv:2610.30114 [cs.DC] |
| (or arXiv:2610.30114v1 [cs.DC] for this version) | |
| https://doi.org/10.48550/arXiv.2610.30114 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Clément Burgelin [view email]
[v1]
Wed, 21 Oct 2026 17:55:19 UTC (556 KB)
来源：arXiv cs.AI · arxiv.org