Paper Overview
Research Area: NLP Authors: Ziyu Guo, Rain Liu, Xinyan Chen, Pheng-Ann Heng Published: 2026-05-14 arXiv: 2605.15198
Introduction
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. However, agentic methods incur context-switching latency from external execution, while latent methods lack task generalization and are difficult to train with autoregressive parallelization. To combine their strengths while mitigating their limitations, the authors propose ATLAS, a framework in which a single discrete 'word', termed a functional token, serves both as an agentic operation and a latent representation.
Original Abstract (excerpt)
> 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. However, agentic methods incur context-switching latency from external execution, while latent methods lack task generalization and are difficult to train with autoregressive parallelization. To combine their strengths while mitigating their limitations, we propose ATLAS, a framework in which a single discrete 'word', termed as a functional token, serves both as an agentic operation...
*(Full abstract truncated in the source post.)*
---
*Auto-collected on 2026-05-15.*