Benchmark
MAGMA-Bench
What is MAGMA-Bench?
Long-horizon embodied agents must maintain task-relevant information, coordinate heterogeneous robots, and adapt their decisions as execution unfolds.
- Released
- 2026-10-09
- Evaluates
- Reasoning, Robotics, Robotics & Embodied AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- rule-auto-admitted
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2610.13534
MAGMA-Bench paper
No reported scores are on record for this benchmark yet.