运行时背后的研究
AEROS 围绕一个想法展开：持续学习的具身智能体需要一个身份层（identity layer） — 一个冻结的、可用密码学验证的内核，把"这个 agent 是谁、被允许做什么" 固定下来，与不断增长的能力解耦。沙箱运行时隔离的是 agent 进程能碰什么； 身份层管的是哪个具身个体在行动、在谁的授权下、在什么行为边界内、留下怎样可审计的历史。 OpenShell 管基础设施；AEROS 管个体。
Governable individuals
Governable Individuals: An Identity Layer for Embodied Agents That Keep Learning
立场之作：持续学习的 agent 为什么需要可验证的身份层，以及把它造出来需要什么。
arXiv:2607.05463 技术报告Governed Individuation: Cryptographically Decoupling an Agent's Learning from Its Authority
配套测量研究：身份不变、权限守恒、可审计性与收敛性，在真实治理运行时上逐条建立。
arXiv:2607.04613 代码s20sc/governed-individuation
技术报告背后的实验 harness — 自包含、一条命令复现，每个发表结果都随仓库入库。
github.com →一个计划，四个支柱
运行时的每个核心机制都先作为研究贡献完成开发与评估，再工程化为仓库里对应的子系统。 下面的论文按各自支撑的支柱分组；系列后续论文上 arXiv 后会陆续补充。
运行时与治理
操作架构 + 准入 → 策略 → 契约 → 安全的门链，以及度量这套治理栈的 benchmark。
- arXiv:2604.07039 AEROS: A Single-Agent Operating Architecture with Embodied Capability Modules →
- arXiv:2604.07833 Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution →
- arXiv:2604.11174 EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems →
能力契约与演进
带版本、带签名的能力接口，以及 ECM 系统背后 validator → shadow → canary 的升级路径。
- arXiv:2604.08059 Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-Component-Based Systems, with Embodied Agents as Case Study →
- arXiv:2604.13097 ECM Contracts: Contract-Aware, Versioned, and Governable Capability Interfaces for Embodied Agents →
- arXiv:2604.26689 Regression Test Selection for Updated Capability Modules in Compositional ML Systems via Atomic-Quality Probes →
记忆与身份
学习沉淀为记忆与 persona，identity hash 却始终一动不动。
Fleet 与部署
多机协同、身份稳定的 canary 上线、异构集群中受治理的角色重分配。
- arXiv:2604.11028 Federated Single-Agent Robotics: Multi-Robot Coordination Without Intra-Robot Multi-Agent Fragmentation →
- arXiv:2605.28097 ICAN-Deploy: Identity-Stable Canary Deployment for Safety-Critical Embodied Agents →
- arXiv:2607.04634 Governed Caste Reassignment in Heterogeneous Swarms: An Asymmetric-Trust Protocol with Audited Operator Countersignature →
引用 AEROS
在研究中使用 AEROS，请引用上面对应的论文 — 论文是理论基础，仓库是工程实现。 引用"身份层"这一整体思想时，请引视角文章与技术报告：
@article{qin2026governable,
title = {Governable Individuals: An Identity Layer for Embodied Agents That Keep Learning},
author = {Qin, Xue and Luan, Simin and Yang, Cong and Li, Zhijun},
journal = {arXiv preprint arXiv:2607.05463},
year = {2026}
}
@article{qin2026governed,
title = {Governed Individuation: Cryptographically Decoupling an Agent's Learning from Its Authority},
author = {Qin, Xue and Luan, Simin and Yang, Cong and Li, Zhijun},
journal = {arXiv preprint arXiv:2607.04613},
year = {2026}
}
引用代码库本身可用仓库里自带的 CITATION.cff：
github.com/s20sc/aeros-core。