ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both

ArXi:2605.15198v1 Announce Type: cross Visual reasoning, often interleaved with intermediate visual states, has emerged as a promising direction in the field. A straightforward approach is to directly generate images via unified models during reasoning, but this is computationally expensive and architecturally non-trivial. Recent alternatives include agentic reasoning through code or tool calls, and latent reasoning with learnable hidden embeddings.