Show-Harness: Just a VLM Agent Can Play Robots

Hugging Face Daily Papers Papers
vision-language-model robot-control zero-shot fine-tuning embodied-ai

Summary

Show-Harness is a method that enables vision-language models to control robots through discrete semantic actions, allowing zero-shot deployment and efficient fine-tuning across different robots and GUIs.

Foundation vision-language models (VLMs) exhibit broad intelligence about the world, yet translating this intelligence into robot control remains challenging. We present Show-Harness, an Embodied Harness that enables VLMs to "play" robots through a compact semantic interface linking intent to action. Show-Harness exposes discrete semantic action units that VLMs can naturally reason over, while embodiment-specific interpreters deterministically ground them into local robot actions, keeping the VLM directly responsible for fine-grained physical decisions. Through the same interface, Show-Harness demonstrates the feasibility of (1) directly unlocking closed-source frontier VLMs for zero-shot robot control, and (2) adapting small-scale open-source VLMs for low-cost deployment with just a few GPU-hours of fine-tuning. We further develop GUMI (GUI Manipulation Interface), which extends the same semantic action space to GUI-based demonstration collection, allowing humans and agents to "play" robots across embodiments without specialized teleoperation hardware. Extensive experiments show that Show-Harness-equipped VLM agents generalize robustly across tasks, embodiments, and environments, outperforming representative agentic and VLA paradigms. These results suggest that the right interface can unlock substantial embodied capability from foundation VLMs, without requiring additional model capacity or costly embodiment-specific pretraining.
Original Article
View Cached Full Text

Cached at: 09/10/26, 02:13 AM

Paper page - Show-Harness: Just a VLM Agent Can Play Robots

Source: https://huggingface.co/papers/2609.10522

Abstract

Show-Harness links vision-language models to robot control via discrete semantic actions interpreted by embodiment-specific modules, enabling zero-shot and efficient fine-tuned deployment across robots and GUIs.

Foundationvision-language models(VLMs) exhibit broad intelligence about the world, yet translating this intelligence into robot control remains challenging. We presentShow-Harness, anEmbodied Harnessthat enables VLMs to “play” robots through a compact semantic interface linking intent to action.Show-Harnessexposes discretesemantic action unitsthat VLMs can naturally reason over, whileembodiment-specific interpretersdeterministically ground them into local robot actions, keeping the VLM directly responsible for fine-grained physical decisions. Through the same interface,Show-Harnessdemonstrates the feasibility of (1) directly unlocking closed-source frontier VLMs forzero-shot robot control, and (2) adapting small-scale open-source VLMs for low-cost deployment with just a few GPU-hours of fine-tuning. We further developGUMI(GUI Manipulation Interface), which extends the same semantic action space to GUI-based demonstration collection, allowing humans and agents to “play” robots across embodiments without specialized teleoperation hardware. Extensive experiments show thatShow-Harness-equipped VLM agents generalize robustly across tasks, embodiments, and environments, outperforming representative agentic andVLA paradigms. These results suggest that the right interface can unlock substantial embodied capability from foundation VLMs, without requiring additional model capacity or costly embodiment-specific pretraining.

View arXiv pageView PDFProject pageGitHubAdd to collection

Get this paper in your agent:

hf papers read 2609\.10522

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper1

#### showlab/Show-Harness-VLMs Image-Text-to-Text• Updated10 minutes ago

Datasets citing this paper1

#### showlab/Show-Harness-Data Viewer• Updated9 minutes ago • 42.6k • 14

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.10522 in a Space README.md to link it from this page.

Collections including this paper1

Similar Articles

Self-Harness: Harnesses That Improve Themselves

Hacker News Top

Self-Harness introduces a new paradigm where LLM-based agents iteratively improve their own operating harness by mining model-specific weaknesses, proposing harness modifications, and validating them through regression testing, achieving substantial performance gains on Terminal-Bench-2.0 across multiple base models.

HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness

Hugging Face Daily Papers

Introduces HarnessBridge, a learnable bidirectional controller that parameterizes the agent-environment interface for LLM agents, achieving performance comparable to specialized harnesses with reduced computational overhead on Terminal-Bench and SWE-bench.