Benchmark RadarAI BENCHMARK PROFILE
EgoProx
EgoProx evaluates multimodal large language models on egocentric 3D proximity reasoning, with tasks organized along a cognitive hierarchy covering intention, exploration, exploitation, and chain-of-actions reasoning.
- Released
- 2026-05-23
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
It addresses the gap in assessing embodied 3D spatial reasoning in MLLMs, a capability important for robotics and augmented reality applications.
Motivation
Humans constantly reason about 3D proximity, the relations between their body and surrounding objects, to guide perception and action in daily life.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.