AI 发现新共识协议 A-greement，延迟最高降低 33.3%
The End of Consensus Research?
AI 智能体帮研究团队发现新共识协议 A-greement，写密集负载延迟降 12.2%、读密集降 33.3%，还顺手用 Lean 验证挖出现有协议漏洞，搞分布式值得看看。
arXiv 论文 2610.30114 报告了一个名为 A-greement 的新共识协议，面向地理分布式状态机复制（SMR）场景。在 5 或 9 副本的六组部署中，A-greement 相比最快基线在写密集和读密集负载下分别将平均延迟降低 12.2% 和 33.3%，只读负载持平。协议核心由租约授权本地读、直连客户端学习写路径和按需选取的固定 quorum 写路径组成。团队的 AI-greement 智能体框架包含协议知识库、模块化实现骨架和基于 Lean 的验证框架，其形式化验证还在现有共识协议中发现了此前未报告的漏洞。论文同时强调人类专家在协议搜索的前中后期仍不可或缺。
The End of Consensus Research?
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.