语义法定数保证：面向非确定性AI基础设施的集体认证
Semantic Quorum Assurance: Collective Certification for Non-Deterministic AI Infrastructure
AI总结：
提出语义法定数保证（SQA），一种通过多样化验证者群体和风险自适应法定数谓词，将非确定性LLM代理的不安全操作批准率从18.5%降至0.3%的控制平面原语。
摘要：
随着大型语言模型（LLM）代理被集成到自主云操作中，分布式系统面临一个语义可靠性问题：提议代理可以生成语法有效且静态授权但操作不安全的生成突变，例如修改IAM策略、开放防火墙安全组或执行数据导出。经典的分布式共识协议复制确定性状态转换，但不评估提议意图的安全性。为弥补这一差距，我们引入语义法定数保证（SQA），一种用于治理非确定性代理基础设施的控制平面原语。SQA将提议表示为绑定到密码证据链的声明性执行合约，并将其路由到由只读、沙盒验证代理组成的多样化面板。SQA在风险自适应法定数谓词下聚合其判断，该谓词强制执行模型和原型多样性，根据校准的保证分数调整权重，并尊重特定原型的否决。通过的提议仅通过主权执行门执行。我们在云原生控制平面中实例化SQA，并为非确定性验证者形式化了一个相关的认知失败模型。在500个基础设施启发的突变场景中，安全结果报告在保留的安全/不安全试验上（排除模糊场景），SQA将不安全批准率从单代理验证的18.5%降低到0.3%，同时在研究风险桶中增加了1.45-4.12秒的中位验证延迟。
英文摘要：
As large language model (LLM) agents are integrated into autonomous cloud operations, distributed systems face a semantic reliability problem: proposer agents can generate production mutations, such as modifying IAM policies, opening firewall security groups, or executing data exports, that are syntactically valid and statically authorized but operationally unsafe. Classical distributed consensus protocols replicate deterministic state transitions but do not evaluate the safety of the proposed intent. To address this gap, we introduce Semantic Quorum Assurance (SQA), a control-plane primitive for governing non-deterministic agentic infrastructure. SQA represents proposals as declarative execution contracts bound to cryptographic evidence chains and routes them to a diverse panel of read-only, sandboxed validator agents. SQA aggregates their judgments under a risk-adaptive quorum predicate that enforces model and archetype diversity, adjusts weights based on calibrated assurance scores, and respects archetype-specific vetoes. Admitted proposals execute only through a sovereign execution gate. We instantiate SQA in a cloud-native control plane and formalize a correlated cognitive failure model for non-deterministic validators. On 500 infrastructure-inspired mutation scenarios, with safety results reported on held-out safe/unsafe trials excluding ambiguous scenarios, SQA reduces unsafe approval from 18.5% for single-agent validation to 0.3% while adding median validation latency of 1.45--4.12 seconds across the studied risk buckets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
