Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs Paper • 2603.20209 • Published 23 days ago • 1
Sleeping Agents 1 KidGym Playground 🧸 1 Play and solve AI gym puzzles with step‑by‑step actions
Sleeping Agents 1 KidGym Playground 🧸 1 Play and solve AI gym puzzles with step‑by‑step actions
Sleeping Agents 1 KidGym Playground 🧸 1 Play and solve AI gym puzzles with step‑by‑step actions