16 papers · 1 filter
Bounded-Fidelity Sim-as-Demo-Stage: Mocap Handoff for Governance Benchmarks
Xue Qin, Simin Luan, Cong Yang +1
Sim-to-real research pursues physics fidelity as a primary objective: simulators are judged by how closely they reproduce real-world contact dynamics. For governance benchmarking o…
Audit-First Rollback Semantics for Safety-Critical Deployment Pipelines
Xue Qin, Simin Luan, Cong Yang +1
Distributed deployment runtimes carry a coherence obligation that classical fault-tolerance frameworks do not name directly: the live state a component is configured to run and the…
Federated Trust for Embodied Robot Capability Marketplaces
Xue Qin, Simin Luan, Cong Yang +1
Robot capability marketplaces, the "app store for robot skills," are emerging as the deployment vector for LLM-driven robot fleets. The default cloud-native answer to "is this pack…
Governable Individuals: An Identity Layer for Embodied Agents That Keep Learning
Xue Qin, Simin Luan, Cong Yang +1
Embodied artificial intelligence is moving from deployable models to persistent agents that learn in the field, acquire skills and migrate across bodies. Governing such a system me…
Governed Caste Reassignment in Heterogeneous Swarms: An Asymmetric-Trust Protocol with Audited Operator Countersignature
Xue Qin, Simin Luan, Cong Yang +1
In heterogeneous robot swarms, caste reassignment (rebinding a robot to a new capability-bound role) is a high-frequency runtime event driven by battery, payload, and priority chan…
Governed Individuation: Cryptographically Decoupling an Agent's Learning from Its Authority
Xue Qin, Simin Luan, Cong Yang +1
Autonomous agents are moving from sandboxed text generators to operators of code, data, and physical infrastructure, and they increasingly learn while deployed. This reopens a ques…
Episodic-to-Semantic Consolidation Without Identity Drift
Xue Qin, Simin Luan, Cong Yang +1
Long-running adaptive intelligent agents face a structural tension between knowledge consolidation and information integrity. Memory consolidation is conventionally treated as an a…
ICAN-Deploy: Identity-Stable Canary Deployment for Safety-Critical Embodied Agents
Xue Qin, Simin Luan, John See +3
Canary deployment routes a fraction of traffic to a new software version, monitors metrics, and rolls back on regression. Mainstream controllers (Argo Rollouts, Spinnaker, Flagger)…
Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-Component-Based Systems, with a Proof-of-Concept Evaluation on Embodied Agents
Xue Qin, Simin Luan, John See +3
Systems built from versioned AI components need lifecycle-time governance over how a new module version is admitted, monitored, and withdrawn. Established deployment patterns (cana…
AEROS: A Single-Agent Operating Architecture with Embodied Capability Modules
Xue Qin, Simin Luan, John See +2
Robotic systems lack a principled abstraction for organizing intelligence, capabilities, and execution in a unified manner. Existing approaches either couple skills within monolith…
Federated Single-Agent Robotics: Multi-Robot Coordination Without Intra-Robot Multi-Agent Fragmentation
Xue Qin, Simin Luan, John See +2
As embodied robots move toward fleet-scale operation, multi-robot coordination is becoming a central systems challenge. Existing approaches often treat this as motivation for incre…
Evolving Skill Modules under a Fixed Planner: Versioning, Rollback, and Runtime Governance for Long-Lived Robot Systems
Xue Qin, Simin Luan, John See +2
Robots deployed for long periods keep improving their skills, and each update changes a released system. We treat this as a software-lifecycle problem: a fixed decision layer dispa…
EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems
Xue Qin, Simin Luan, John See +2
Recent progress in embodied AI has produced a growing ecosystem of robot policies, foundation models, and modular runtimes. However, current evaluation remains dominated by task su…
Regression Test Selection for Updated Capability Modules in Compositional ML Systems via Atomic-Quality Probes
Xue Qin, Simin Luan, Cong Yang +1
Compositional machine-learning (ML) systems assemble runtime behavior from libraries of independently re-trained capability modules. Replacing one module raises a regression-testin…
ECM Contracts: Contract-Aware, Versioned, and Governable Capability Interfaces for Embodied Agents
Xue Qin, Simin Luan, Cong Yang +1
Embodied agents increasingly rely on modular capabilities that are installed, upgraded, composed, and governed at runtime, yet the interfaces between these modules are specified on…
Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution
Xue Qin, Simin Luan, John See +3
Embodied Agents are evolving from passive reasoning systems into active executors that interact with tools, robots, and physical environments. Once an agent gains execution authori…