Paper Overview
- Field: NLP / Visual Reasoning
- Authors: Ziyu Guo, Rain Liu, Xinyan Chen, Pheng-Ann Heng
- Posted: 2026-05-14
- arXiv: 2605.15198
- Agentic reasoning through code or tool calls — incurs context-switching latency from external execution.
- Latent reasoning with learnable hidden embeddings — lacks task generalization and is difficult to train with autoregressive parallelization.
Introduction
Visual reasoning, often interleaved with intermediate visual states, has emerged as a promising direction in the field. This paper proposes ATLAS, a framework that unifies agentic and latent visual reasoning through a single functional token.
Background and Motivation
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:
Proposed Approach
To combine the strengths of both paradigms while mitigating their limitations, the authors propose ATLAS, in which a single discrete 'word' — termed a functional token — serves both as an agentic operation and as a latent reasoning representation.
Original Abstract (English)
> 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...
---
*Auto-collected on 2026-05-15*