为自主AI设计可验证的状态变更日志，大幅降低数据开销并提升安全性。
Agent-Native Telemetry: Verifiable State-Delta Evidence for Autonomous Operations
- 用可验证的状态差分替代冗长文本日志，聚焦系统状态变化。
- 在基准测试中减少96.4%网络传输量、88.8%大模型上下文消耗。
- 适合需要高安全性和低延迟的自治系统，如AIOps与微服务监控。
现有运行时遥测主要面向人类阅读：系统反复序列化冗长文本、静态键值和重复上下文，产生数十亿条日志行。随着自主AI代理成为主要操作消费方，传统日志浪费其有限的上下文容量，用于解析语法而非推理系统状态变化，且缺乏来源与完整性的密码学保障。本文提出代理原生遥测（Agent-Native Telemetry），基于可验证状态差分构建自主机器操作者的运行证据架构。提出代理遥测协议（ATP）与状态差分证据账本，将操作事实结构化为四种核心证据原语（状态转移、观测、关系、状态快照），采用内容寻址模式，将未净化文本作为摘要验证的不可读引用。生产者对批次签名并哈希链化以实现原子追加。经验证的记录通过两条并行路径供给代理：无状态协议解码器输出紧凑位置行，有状态语义网关提供有限图胶囊。证明了信息保真下界，并形式化了账本相对的可验证否定定理，实现事件不存在的可信证明。在分布式微服务基准（AIOpsLab 和 OpenTelemetry Astronomy Shop）上，ATP相比OpenTelemetry JSON减少96.4%原始网络负载和建模云查询扫描成本，降低88.8%大模型上下文令牌使用与66.2%查询操作数，检测到全部500次恶意存储变异，且在每种配置下50次对抗性测试中均实现零成功提示注入。
原文摘要 · Abstract (English)
Operational telemetry is predominantly engineered for human reading: systems repeatedly serialize verbose prose, static keys, and redundant context across billions of log lines. As autonomous AI agents become primary operational consumers, feeding them traditional logs wastes scarce context capacity parsing lexical syntax rather than reasoning over system state changes -- all while lacking cryptographic guarantees of provenance or collection completeness. This paper introduces agent-native telemetry, an operational evidence architecture for autonomous machine operators founded on verifiable state deltas rather than human prose. We present the Agent Telemetry Protocol (ATP) and the State-Delta Evidence Ledger, an implementation that structures operational facts into four core evidence primitives (Transitions, Observations, Relations, and State Checkpoints) governed by content-addressed schemas, while isolating uncurated text as digest-verified opaque references. Producers sign and hash-chain batches for atomic collector append. Verified records feed two parallel agent access paths: a stateless protocol decoder emitting compact positional rows, and a stateful semantic gateway serving bounded graph capsules. We prove an information-preservation lower bound and formalize a ledger-relative verified negative theorem for provable event non-occurrence. On distributed microservice benchmarks (AIOpsLab and OpenTelemetry Astronomy Shop), ATP reduces raw wire payload and modeled cloud query scan costs by 96.4% relative to OpenTelemetry JSON, reduces LLM context tokens by 88.8% and query operations by 66.2%, detects all 500 tested adversarial storage mutations, and yields zero successful prompt injections across 50 adversarial trials per ATP configuration.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。