Zhejiang University's RoboHarness Lets LLM Agents Beat VLA Models on BEHAVIOR
zju · hf · 2026-10-27
Researchers at Zhejiang University argue that generalist embodied manipulation doesn't require training specialized VLA models. Their RoboHarness gives LLM coding agents a visual-geometric control panel so they can directly understand and invoke embodied tasks.
- With the harness, Qwen3.8-Flash-Next outperforms state-of-the-art VLA models on BEHAVIOR Challenge 2025 tasks.
- Implementation is open source on GitHub.
More from Embodied
- From 5-Word Prompt to Physical Product: AI Designs and 3D-Prints a Filter Holder — blixt · 2026-10-27
- NVIDIA opens ARIEL lab in Singapore, hiring agentic robotics research scientist interns — DJiafei · 2026-10-27
- He let Claude design a complete e-ink business card, from schematic to product page — isaul32 · 2026-10-27
- EmbodiedLab Benchmarks Robots That Must Act to Know in Simulated Labs — HexaFuture · 2026-10-27
- VAST's EdenLive renders AI-generated 720p game worlds at 24 FPS on one RTX 5090 — jiqizhixin · 2026-10-27
- Tesla FSD safety data shows 9x longer gap between major crashes than manual driving — Scobleizer · 2026-10-27