# AEROS: A Single-Agent Operating Architecture with Embodied Capability Modules arXiv: https://arxiv.org/abs/2604.07039 ยท HTML: https://mlsanity.com/paper/2604.07039/ ## Key facts - Cited by 7 papers in the map (data through 14 Oct 2026). - Builds on 23 of its 55 references that are in the map. - First posted on arXiv 8 Apr 2026. ## Builds on (most cited first, 23 of 23) - [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023) - [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022) - [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023) - [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023) - [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022) - [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023) - [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022) - [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022) - [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023) - [ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills](https://mlsanity.com/paper/2302.04659/) (2023) - [ChatGPT for Robotics: Design Principles and Model Abilities](https://mlsanity.com/paper/2306.17582/) (2023) - [Integrated Task and Motion Planning](https://mlsanity.com/paper/2010.01083/) (2020) - [Robot Operating System 2: Design, Architecture, and Uses In The Wild](https://mlsanity.com/paper/2211.07752/) (2022) - [BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation](https://mlsanity.com/paper/2403.09227/) (2024) - [Behavior Trees in Robotics and AI: An Introduction](https://mlsanity.com/paper/1709.00084/) (2017) - [RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration](https://mlsanity.com/paper/2505.03673/) (2025) - [EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents](https://mlsanity.com/paper/2410.22662/) (2024) - [Safety Aware Task Planning via Large Language Models in Robotics](https://mlsanity.com/paper/2503.15707/) (2025) - [RoboMatrix: A Skill-centric Hierarchical Framework for Scalable Robot Task Planning and Execution in Open-World](https://mlsanity.com/paper/2412.00171/) (2024) - [CoSTAR: Instructing Collaborative Robots with Behavior Trees and Vision](https://mlsanity.com/paper/1611.06145/) (2016) - [LLM-as-BT-Planner: Leveraging LLMs for Behavior Tree Generation in Robot Task Planning](https://mlsanity.com/paper/2409.10444/) (2024) - [Enabling Novel Mission Operations and Interactions with ROSA: The Robot Operating System Agent](https://mlsanity.com/paper/2410.06472/) (2024) - [Robotics Software Engineering: A Perspective from the Service Robotics Domain](https://mlsanity.com/paper/2006.10608/) (2020) ## Built on by (most cited first, 7 of 7) - [Evolving Skill Modules under a Fixed Planner: Versioning, Rollback, and Runtime Governance for Long-Lived Robot Systems](https://mlsanity.com/paper/2604.07799/) (2026) - [Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-Component-Based Systems, with a Proof-of-Concept Evaluation on Embodied Agents](https://mlsanity.com/paper/2604.08059/) (2026) - [HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memory](https://mlsanity.com/paper/2606.23565/) (2026) - [Teach and Grow: An Agent-Centered Architecture for General Robot Learning](https://mlsanity.com/paper/2608.17209/) (2026) - [Federated Single-Agent Robotics: Multi-Robot Coordination Without Intra-Robot Multi-Agent Fragmentation](https://mlsanity.com/paper/2604.11028/) (2026) - [Regression Test Selection for Updated Capability Modules in Compositional ML Systems via Atomic-Quality Probes](https://mlsanity.com/paper/2604.26689/) (2026) - [MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention](https://mlsanity.com/paper/2606.01063/) (2026) ## Abstract (arXiv) Robotic systems lack a principled abstraction for organizing intelligence, capabilities, and execution in a unified manner. Existing approaches either couple skills within monolithic architectures or decompose functionality into loosely coordinated modules or multiple agents, often without a coherent model of identity and control authority. We argue that a robot should be modeled as a single persistent intelligent subject whose capabilities are extended through installable packages. We formalize this view as AEROS (Agent Execution Runtime Operating System), in which each robot corresponds to one persistent agent and capabilities are provided through Embodied Capability Modules (ECMs). Each ECM encapsulates executable skills, models, and tools, while execution constraints and safety guarantees are enforced by a policy-separated runtime. This separation enables modular extensibility, composable capability execution, and consistent system-level safety. We evaluate a reference implementation in PyBullet simulation with a Franka Panda 7-DOF manipulator across eight experiments covering re-planning, failure recovery, policy enforcement, baseline comparison, cross-task generality, ECM hot-swapping, ablation, and failure boundary analysis. Over 100 randomized trials per condition, AEROS achieves 100% task success across three tasks versus baselines (BehaviorTree.CPP-style and ProgPrompt-style at 92--93%, flat pipeline at 67--73%), the policy layer blocks all invalid actions with zero false acceptances, runtime benefits generalize across tasks without task-specific tuning, and ECMs load at runtime with 100% post-swap success.