# Octopus Protocol: One-Shot Hardware Discovery and Control for AI Agents via Infrastructure-as-Prompts

arXiv: https://arxiv.org/abs/2605.09055 · HTML: https://mlsanity.com/paper/2605.09055/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 9 May 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)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [Robot Operating System 2: Design, Architecture, and Uses In The Wild](https://mlsanity.com/paper/2211.07752/) (2022)
- [AIOS: LLM Agent Operating System](https://mlsanity.com/paper/2403.16971/) (2024)
- [Reducing the Barrier to Entry of Complex Robotic Software: a MoveIt! Case Study](https://mlsanity.com/paper/1404.3785/) (2014)
- [CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation](https://mlsanity.com/paper/2603.22435/) (2026)
- [RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks](https://mlsanity.com/paper/2603.11558/) (2026)
- [Specifications: The missing link to making the development of LLM systems an engineering discipline](https://mlsanity.com/paper/2412.05299/) (2024)
- [Enabling Novel Mission Operations and Interactions with ROSA: The Robot Operating System Agent](https://mlsanity.com/paper/2410.06472/) (2024)
- [From REST to MCP: An Empirical Study of API Wrapping and Automated Server Generation for LLM Agents](https://mlsanity.com/paper/2507.16044/) (2025)
- [IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol](https://mlsanity.com/paper/2510.01260/) (2025)
- [Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments](https://mlsanity.com/paper/2411.00186/) (2024)
- [TerraFormer: Automated Infrastructure-as-Code with LLMs Fine-Tuned via Policy-Guided Verifier Feedback](https://mlsanity.com/paper/2601.08734/) (2026)
- [RoboNeuron: A Middle-Layer Infrastructure for Agent-Driven Orchestration in Embodied AI](https://mlsanity.com/paper/2512.10394/) (2025)
- [Skilled AI Agents for Embedded and IoT Systems Development](https://mlsanity.com/paper/2603.19583/) (2026)
- [ROSClaw: An OpenClaw ROS 2 Framework for Agentic Robot Control and Interaction](https://mlsanity.com/paper/2603.26997/) (2026)
- [Robot Context Protocol (RCP): A Runtime-Agnostic Interface for Agent-Aware Robot Control](https://mlsanity.com/paper/2506.11650/) (2025)

## Abstract (arXiv)

Bringing a previously unintegrated device under the control of an AI agent still requires device-specific engineering: driver selection, dependency resolution, interface design, and deployment, repeated per device and per platform. We present Octopus, a hardware onboarding framework in which a coding agent, rather than a shipped integration, is the runtime that produces the required infrastructure. Given shell access and a model API key, a single bootstrap command drives the agent through a five-stage pipeline that enumerates operating-system- visible hardware, infers device identity and capabilities, generates typed Model Context Protocol tools and the hardware-facing code behind them, and activates the result as a live endpoint. A persistent daemon then maintains the result, repairing defined classes of failure in the deployment it produced. Across four hosts spanning two processor architectures, three operating- system families, and two device-access paths, identical prose specifications produced working interfaces with no per-host edits and no hand-written integration code. Five consecutive runs on the reference host completed end to end on first attempt. We report both the resulting capability and a failure mode of unattended repair loops observed over eleven hours of continuous operation.