Benchmark RadarAI BENCHMARK PROFILE
The Image Reconstruction Game
A benchmark for iterative multimodal dialogue where a vision-language model issues corrective instructions to an image generator over multiple turns, with accumulated common ground observable as a rendered image.
- Released
- 2026-06-01
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Addresses the evaluation of interactive language-vision systems and common ground building, but lacks a clear public comparison path.
Motivation
We introduce the Image Reconstruction Game, a fully automated benchmark in which a vision-language model issues corrective instructions to an image generator across multiple turns, making accumulated common ground directly observable as a rendered image.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.