OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning

Fanqi Lin, Ruiqian Nai, Yingdong Hu, Jiacheng You, Junming Zhao, Yang Gao

Keywords: Vision-Language-Action Models, Embodied Reasoning

TL;DR: We present OneTwoVLA, a single unified vision-language-action model capable of both reasoning and acting, and can adaptively decide when to reason and when to act.

Abstract:

General-purpose robots capable of performing diverse tasks require synergistic reasoning and acting capabilities.
However, recent dual-system approaches, which separate high-level reasoning from low-level acting, often suffer from challenges such as limited mutual understanding of capabilities between systems and latency issues.
This paper introduces OneTwoVLA, a single unified vision-language-action model that can perform both acting (System One) and reasoning (System Two). Crucially, OneTwoVLA adaptively switches between two modes: explicitly reasoning at critical moments during task execution, and generating actions based on the most recent reasoning at other times.
To further unlock OneTwoVLA's reasoning and generalization capabilities, we design a scalable pipeline for synthesizing embodied reasoning-centric vision-language data, used for co-training with robot data. We validate OneTwoVLA's effectiveness through extensive experiments, highlighting its superior performance across four key capabilities: long-horizon task planning, error detection and recovery, natural human-robot interaction, and generalizable visual grounding, enabling the model to perform long-horizon, highly dexterous manipulation tasks such as making hotpot or mixing cocktails.

Submission Number: 34