EmbodiedLab: Benchmarking Embodied Agents That Act to Know
- Published
- Source
- arXiv
- Paper number
- 1380
- Field
- Robotics
- arXiv ID
- 2610.35385
Key points
- EmbodiedLab runs 30 experiments in five disciplines on 14 apparatus platforms, giving the agent only the objective and the apparatus while it chooses its own procedure.
- A run succeeds only if its result lies within the instrument tolerance, rests on readings recorded in the same episode, and leaves the bench in the state the task requires.
- Evaluating six frontier models, the highest success rate at the lowest interface level T0 is 43.3% by Claude Opus 5.5, followed by GPT-6 Astra at 40.0%.
- Acting on the apparatus, observing it, and restoring it account for 75% to 100% of every agent's failed runs, while at most 25% fail in reasoning from readings already in hand.
- Adding perception and motion planning at T1 raises the success rate by at most 10 points, while manipulation skills at T2 raise the weaker agents by 10 to 27 points.
Paper links
External research summaries. These are not HDATF publications or measured product results.