[2603.01490] ATA: Bridging Implicit Reasoning with Attention-Guided and Action-Guided Inference for Vision-Language Action Models

Computer Science > Computer Vision and Pattern Recognition arXiv:2603.01490 (cs) [Submitted on 2 Mar 2026] Title:ATA: Bridging Implicit Reasoning with Attention-Guided and Action-Guided Inference for Vision-Language Action Models Authors:Cheng Yang, Jianhao Jiao, Lingyi Huang, Jinqi Xiao, Zhexiang Tang, Yu Gong, Yibiao Ying, Yang Sui, Jintian Lin, Wen Huang, Bo Yuan View a PDF of the paper titled ATA: Bridging Implicit Reasoning with Attention-Guided and Action-Guided Inference for Vision-Language Action Models, by Cheng Yang and 10 other authors View PDF HTML (experimental) Abstract:Vision-Language-Action (VLA) models rely on current observations, including images, language instructions, and robot states, to predict actions and complete tasks. While accurate visual perception is crucial for precise action prediction and execution, recent work has attempted to further improve performance by introducing explicit reasoning during inference. However, such approaches face significant limitations. They often depend on data-intensive resources such as Chain-of-Thought (CoT) style annotations to decompose tasks into step-by-step reasoning, and in many cases require additional visual grounding annotations (e.g., bounding boxes or masks) to highlight relevant image regions. Moreover, they involve time-consuming dataset construction, labeling, and retraining, which ultimately results in longer inference sequences and reduced efficiency. To address these challenges, we propose ATA, a...