DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Models

TL;DR

DualCoT-VLA introduces a parallel reasoning approach combining visual and linguistic chain-of-thoughts to enhance complex task planning and spatial understanding in vision-language-action models, reducing inference latency and improving performance.

Contribution

It presents a novel parallel reasoning mechanism with dual visual and linguistic CoT, enabling comprehensive multi-modal reasoning and efficient inference in VLA models.

Findings

Achieves state-of-the-art results on LIBERO and RoboCasa GR1 benchmarks.

Demonstrates improved reasoning and manipulation capabilities in real-world robotic tasks.

Reduces inference latency compared to autoregressive CoT methods.

Abstract

Vision-Language-Action (VLA) models map visual observations and language instructions directly to robotic actions. While effective for simple tasks, standard VLA models often struggle with complex, multi-step tasks requiring logical planning, as well as precise manipulations demanding fine-grained spatial perception. Recent efforts have incorporated Chain-of-Thought (CoT) reasoning to endow VLA models with a ``thinking before acting'' capability. However, current CoT-based VLA models face two critical limitations: 1) an inability to simultaneously capture low-level visual details and high-level logical planning due to their reliance on isolated, single-modal CoT; 2) high inference latency with compounding errors caused by step-by-step autoregressive decoding. To address these limitations, we propose DualCoT-VLA, a visual-linguistic CoT method for VLA models with a parallel reasoning mechanism. To achieve comprehensive multi-modal reasoning, our method integrates a visual CoT for low-level spatial understanding and a linguistic CoT for high-level task planning. Furthermore, to overcome the latency bottleneck, we introduce a parallel CoT mechanism that incorporates two sets of learnable query tokens, shifting autoregressive reasoning to single-step forward reasoning. Extensive experiments demonstrate that our DualCoT-VLA achieves state-of-the-art performance on the LIBERO and RoboCasa GR1 benchmarks, as well as in real-world platforms.