Embodied First Exam launches as the first physical-world benchmark for code agents
ManlingLi_ · x · 2026-10-20
Manling Li's team launched Embodied First Exam, a benchmark asking what the first physical-world exam for code agents looks like after they've passed many digital-world exams. The project is open for contributions via website, technical report, code, and Discord — inviting researchers to bring their own agents and task suites. A unified interface drives real robots directly, demonstrated with a real buzz-wire run, with task diversity, transparent scoring rules, and a public leaderboard.
More from Embodied
- Robotics take: IK guarantees no precision edge, hardware—not the solver—is the bottleneck — ChongZzZhang · 2026-10-20
- MPC vs RL for robot tracking: the precision bottleneck is hardware, not the solver — ChongZzZhang · 2026-10-20
- The most important AI device of the next decade won't be a smartphone — VraserX · 2026-10-20
- NUS MAGIC Lab is hiring a postdoc, 2 PhD students and 3 research assistants for robotics — DJiafei · 2026-10-20
- AlphaNIST two-finger gripper screws nuts multiple ways, "it's just PPO" — _Stocko_ · 2026-10-20
- New RL paper: C-Slerp learns 5-cube stacking from scratch with no rewards or pretraining — ben_eysenbach · 2026-10-20