---
title: "Ant Group's LingBot-VLA Opens 20,000 Hours of Real Robot Training Data"
subtitle: "Robbyant open-sources LingBot-VLA, a 4B-parameter dual-arm robot foundation model trained on 20,000 hours of real-world teleoperation data across 9 robot configurations."
url: "https://alphasignal.ai/news/ant-group-s-lingbot-vla-opens-20-000-hours-of-real-robot-training-data"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-06-11T16:51:17.000Z"
updated: "2026-06-20T07:56:45.754Z"
type: "Repo"
topics:
  - "Robotics"
  - "Open Source"
subtopics:
  - "Vla Models"
  - "Manipulation"
upvotes: 15
source_url: "https://github.com/Robbyant/lingbot-vla"
comments: 0
truncated: true
---

# Ant Group's LingBot-VLA Opens 20,000 Hours of Real Robot Training Data

> Robbyant open-sources LingBot-VLA, a 4B-parameter dual-arm robot foundation model trained on 20,000 hours of real-world teleoperation data across 9 robot configurations.

[Robbyant](https://github.com/Robbyant/lingbot-vla), the embodied intelligence arm of Ant Group, has fully open-sourced **LingBot-VLA** , releasing code, pretrained weights, and benchmark data for a Vision-Language-Action (VLA) foundation model built specifically for dual-arm robot manipulation. The release includes two model variants, training scripts, deployment configs, and the GM-100 benchmark dataset, all under the Apache 2.0 license.

VLA models are robot policies that take camera images and natural language instructions as input and output low-level motor actions , essentially giving robots the ability to understand instructions and act on them. Most existing VLA models are either trained on limited data, tied to a single robot platform, or too slow to train at scale. LingBot-VLA is designed to address all three at once.

## 20,000 hours of real-world robot data

LingBot-VLA is a Qwen2.5-VL-based VLA foundation model trained on about 20,000 hours of real-world dual-arm teleoperation across 9 robot embodiments, enabling strong cross-morphology and cross-task generalization. The robot configurations covered include AgiBot G1, AgileX, Galaxea R1Lite, Galaxea R1Pro, Realman Rs-02, Leju KUAVO 4 Pro, Qinglong humanoid, ARX Lift2, and a Bimanual Franka setup.

Systematic pre-training data scaling experiments showed that success rates climbed consistently across all three evaluation platforms with no saturation at 20K hours, suggesting continued benefit from additional diverse real-world data. In other words, the model hasn't hit a ceiling yet , more data should keep improving it.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [Robbyant/lingbot-vla GitHub Repository](https://github.com/Robbyant/lingbot-vla)
- [A Pragmatic VLA Foundation Model — arXiv:2601.18692](https://arxiv.org/abs/2601.18692)
- [Robbyant Open-Sources LingBot-VLA as a Universal Brain for Robots — BusinessWire](https://secure.businesswire.com/news/home/20260127455032/en/Robbyant-Open-Sources-LingBot-VLA-as-a-Universal-Brain-for-Robots)
- [LingBot-VLA: 17.3% Success Rate on 100 Dual-Arm Manipulation Tasks](https://industrialmonitordirect.com/blogs/knowledgebase/lingbot-vla-scaling-results-173-sr-with-depth-distillation)
- [robbyant/lingbot-vla-4b — HuggingFace](https://huggingface.co/robbyant/lingbot-vla-4b)