# TypeGo: An OS Runtime for Embodied Agents

arXiv: https://arxiv.org/abs/2607.05482 · HTML: https://mlsanity.com/paper/2607.05482/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 29 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 18 of 18)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (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)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Hierarchical Reasoning Model](https://mlsanity.com/paper/2506.21734/) (2025)
- [Large Language Models for Robotics: A Survey](https://mlsanity.com/paper/2311.07226/) (2023)
- [AIOS: LLM Agent Operating System](https://mlsanity.com/paper/2403.16971/) (2024)
- [OK-Robot: What Really Matters in Integrating Open-Knowledge Models for Robotics](https://mlsanity.com/paper/2401.12202/) (2024)
- [BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation](https://mlsanity.com/paper/2410.06237/) (2024)
- [Language-Conditioned Robotic Manipulation with Fast and Slow Thinking](https://mlsanity.com/paper/2401.04181/) (2024)
- [Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinking](https://mlsanity.com/paper/2502.12470/) (2025)
- [OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network](https://mlsanity.com/paper/2209.05946/) (2022)
- [LLM Augmented Hierarchical Agents](https://mlsanity.com/paper/2311.05596/) (2023)
- [How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2602.02103/) (2026)
- [Learning Hierarchical Domain Models Through Environment-Grounded Interaction](https://mlsanity.com/paper/2505.13497/) (2025)

## Abstract (arXiv)

Large language models (LLMs) can plan behavior for embodied agents from natural language, but treating the LLM as a request/response oracle on the critical path is fundamentally at odds with real-time control and concurrent goals. We argue for an operating-system-style runtime for embodied agents, and instantiate this idea in an early prototype, TypeGo. TypeGo structures LLM-based planning as asynchronous loops at multiple timescales that overlap with execution, and manages the agent's physical body like an OS manages hardware: the Skill Kernel arbitrates typed physical subsystems among concurrent per-task processes, a scheduler preempts them and resumes or replaces each by source, and speculative skill streaming hides LLM latency behind ongoing motion, while a fast first-action path yields visible feedback within a second. Users program behavior through natural language prescriptions that TypeGo dispatches to the LLM-based planners or compiles into low-latency interrupt handlers. Our prototype of Kalos, a Unitree Go2 quadruped, provides preliminary evidence for the design: in our current task suite, it cuts per-step delay by 50% over step-by-step planning and time-to-first-action by 73% over monolithic planning, while admitting concurrent tasks at low scheduling overhead.