τ(0)-VLA uses 40,115 hours of robot data to tackle long-horizon tasks
机器之心 · wechat · 2026-07-27
A long WeChat article breaks down τ(0)-VLA, a new embodied AI model aimed at long-horizon robotic tasks. The key idea is to split planning and execution: a high-level “slow thinking” policy handles task decomposition and decision making, while a low-level “fast execution” policy handles real-time control.
What the model adds
- Introduces test-time computation and a world-model-guided planning loop for embodied decision making
- Uses a four-part high-level stack: proposal model, world model, value model, and reflection model
- Builds a beam-search-like mechanism over sub-tasks to reason about chain effects in the physical world
Training and scale
- Trained on 40,115 hours of real robot interaction data
- Includes 20,000+ hours of on-robot data across multiple robot forms and public datasets
- Supports multiple embodiments via a unified 40-dimensional action space and masking for different robots
Reported results
- On AGIBOT G1, hierarchical planning raises average success rate from 27.5% to 45.0% and progress from 80.10% to 87.85%
- The model also shows strong direct-execution performance across several manipulation tasks, with some tasks reaching 10/10 success
The article argues that embodied AI is moving from short demo actions toward long-horizon real-world completion, and that “thinking before acting” may be the key bottleneck to solve.
More from Embodied
- AheadForm unveils an ultra-lifelike humanoid robot at WAIC 2026 in Shanghai — Olivier__OG · 2026-07-27
- Stanford AI Lab cites NVIDIA’s Alpamayo platform as a model for open Physical AI — StanfordAILab · 2026-07-27
- RoboDojo benchmarks 30 robot manipulation policies across 42 sim and 18 real tasks — jiqizhixin · 2026-07-27
- Neuralink's future: Brain implants could potentially eliminate back pain — DimaZeniuk · 2026-07-27
- Insta360 Open-Sources PanoLOG: Breaking Large-Scale 3D Reconstruction Bottlenecks with Panoramic Cameras — 机器之心 · 2026-07-27
- MotionBricks shows modular real-time motion generation for games, robots, and film — maier_ak · 2026-07-27