Huawei's openJiuwen open-sources Jiuwen Symbiosis agent for autonomous wet-lab experiments
机器之心 · wechat · 2026-10-20
Huawei's openJiuwen team demonstrated Jiuwen Symbiosis, a physical agent system that executes LLM-designed experiment protocols on real lab equipment, using electrocatalysis as its showcase, with code open-sourced on AtomGit and GitHub.
The system runs a perceive–plan–act–feedback agent loop: open-vocabulary vision plus depth data for scene awareness; dynamic task orchestration based on explicitly declared device capabilities rather than fixed scripts; safety guardrails triggered before every motion tool call, with recovery returning end effectors to known-safe poses (keeping held samples during retreat); and execution memory with replayable traces that cluster failure causes across runs for continuous improvement.
More from Embodied
- MIT CSAIL's X-Hinges 3D-Prints Everyday Objects With Built-In Sensing Across Three Motion Axes — MIT News AI · 2026-10-23
- Formic raises $50M Series B to scale physical AI across 100+ US factories — garrytan · 2026-10-23
- fal starts fine-tuning a physical robot to draw, results next week — OdinLovis · 2026-10-23
- PEARL demo: an LLM agent that checks experiment results, revises plans, and re-tests — KevinKaichuang · 2026-10-23
- CU Boulder's ATLAS Institute Opens Tenure-Track Robotics Professorship — ryosuzk · 2026-10-23
- MiTaS multi-resolution tactile imitation learning hits 80% success vs 35.5% vision-only baseline — Jan_R_Peters · 2026-10-23