CoHuB: A Simulation Benchmark for Multi-Humanoid Collaboration

What is CoHuB: A Simulation Benchmark for Multi-Humanoid Collaboration?

Evaluates multi-humanoid collaboration policies in simulation under egocentric visual observations across 10 tasks with two or three humanoids.

Released

2026-09-28

Evaluates

General AI, Robotics & Embodied AI, cs.RO

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.34782

CoHuB: A Simulation Benchmark for Multi-Humanoid Collaboration paper

• Paper https://arxiv.org/abs/2609.34782
• Website https://meat124.github.io/CoHuB/

Which sources cite CoHuB: A Simulation Benchmark for Multi-Humanoid Collaboration?

• CoHuB: A Simulation Benchmark for Multi-Humanoid Collaboration

Related General AI, Robotics & Embodied AI, cs.RO benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 2d-fet-bench
• 360CityArena
• 3DCodeBench
• 4DSynth-Nav
• 5-Dialects-BN
• A Real-World CAD Segmentation Benchmark
• A3S-Bench