The paper introduces GTA‑VLA, an interactive Vision‑Language‑Action framework that lets users guide robot policies with explicit visual cues such as affordance points, boxes, and traces. Unlike traditional direct sense‑to‑act models, GTA‑VLA incorporates a spatial‑visual Chain‑of‑Thought that blends human guidance with internal task planning, and couples this reasoning module with a lightweight reactive action head for efficient execution. Experiments on the SimplerEnv WidowX benchmark show a state‑of‑the‑art 81.2 % success rate, and the framework significantly improves task success under out‑of‑domain visual shifts and spatial ambiguities, demonstrating the benefit of interactive reasoning for failure recovery in embodied control.
By Yiran Ling, Qing Lian, Jinghang Li, Qing Jiang, Tianming Zhang, Xiaoke Jiang, Chuanxiu Liu, Jie Liu, Lei Zhang
arXiv:2601. 20334v2 Announce Type: replace-cross Abstract: Robotic manipulation has increasingly adopted vision-language-action (VLA) models, which achieve strong performance but typically require task-specific demonstrations and fine-tuning, and often generalize poorly under domain shift.
By Brian Y. Tsui, Alan Y. Fang, Tiffany J. Hwu
RoboSPA is a large-scale robotic manipulation dataset and benchmark designed to evaluate Vision‑Language‑Action models on fine‑grained spatial reasoning and long‑horizon procedural planning. It contains 10 task categories, 56 base tasks, and 280 variants across five difficulty levels, with 527K trajectories collected from multiple embodiments and scenes. The benchmark introduces diagnostic metrics beyond binary success, revealing that current VLA models struggle with complex spatial relations, precise execution, and memory‑intensive planning.
By Zhenxuan Fan, Bo Zhang, Yutong Lin, Yuqian Yuan, Juekai Lin, Liang Liang, Zhuoyi Huang, Wenqiao Zhang, Juncheng Li, Siliang Tang, Jun Xiao, Yueting Zhuang
ReactHuman is a physics‑grounded benchmark that tests whether multimodal large language models (MLLMs) can make immediate, safety‑critical decisions in simulated humanoid scenarios involving sudden household hazards. The benchmark includes 17 event families, over 1,000 reproducible scenes generated from 240 Hz rigid‑body simulation, and a five‑metric suite evaluating reactions on reasonableness, safety, and physical grounding. Evaluation of seven MLLMs reveals that reactive safety remains unsolved, with models frequently mishandling hazards, relying on appearance over motion, and missing key interception points.
By Yizhan Li, Jianxin You, Mengyang Xiong, Yinhuan Chen, Zicheng Zhao, Dekun Wu, Dongqing Zhang, Bang Liu
arXiv:2607. 09792v1 Announce Type: cross Abstract: Navigation is a fundamental capability of autonomous systems, yet most existing approaches rely on highly structured models and strong prior assumptions, limiting their robustness in open and uncertain real-world environments.
By Liuyi Wang, Kai Sheng, Zongtao He, Jinlong Li, Yongrui Qin, Haojie Dai, Xiangyi Wang, Jingwei Yang, Qingqing Yan, Chengju Liu, Qijun Chen
arXiv:2609.25627v1 Announce Type: cross
Abstract: General-purpose robot control requires models to understand task intent, identify where to interact, capture how the scene evolves, and generate prec...
By Haoran Wen, Wenfu Wang, Kunsong Shi, Jingke Wang, Wancheng Feng, Yiren Zhang, Yueran Zhao, Xuancheng Zhang, Nanfei Ye, Xingru Chen, Zhaohong Sun, Chengmin Yang, Zikang Yu, Penghao Bi, Jia Shi, Yu Liu, Kun Zhan, Yan Xie
RoboPhys-3D is a 3D‑grounded embodied world model benchmark built on RoboTwin 2.0, featuring 50 manipulation tasks, 5,000 episodes, and 25,000 multi‑view ground‑truth videos. It evaluates video world models by processing both generated and ground‑truth videos through the same 3D reconstruction pipeline, allowing the separation of reconstruction‑induced from generation‑induced errors. The benchmark defines 50 metrics across four sub‑dimensions—pixel fidelity, 3D geometry consistency, state understanding, and task completeness—and introduces the Average Full Score and RoboPhyscore for holistic assessment, with RoboPhyscore showing strong correlation with human judgments.
By Tianyi Wang, Jiazhou Chen, Yiming Xu, Xiangyu Li, Tianyi Zeng, Chih-Hsien Chou, Ning Lu, Liang Peng, Junfeng Jiao, Christian Claudel
arXiv:2608.29537v1 Announce Type: cross
Abstract: Frozen vision-language-action (VLA) policies offer broad manipulation skills but execute open-loop action chunks without tracking task progress, so t...
By Hongbo Gao, Zeyu Ni, Xin Wen, Siyu Xu, Ruifeng Li
arXiv:2609.24170v1 Announce Type: new
Abstract: Embodied AI systems are often organized into System 1 and System 2. System 1 is typically a pretrained policy that generates actions at high frequency,...
By Wenbo Zhang, Kaixuan Wang, Yutao Ouyang, Xiaoyu Huang, Liyang Li, Kailun Su, Weiyang Jin, Wenhao Chai, Haotian Liang, Zhiyang Dou, Yue Chen, Tianxing Chen
arXiv:2609.37810v1 Announce Type: cross
Abstract: Vision-language-action and world-action models have demonstrated impressive capabilities in robotics, yet generalization to unseen tasks remains chal...
By Sicheng Xie, Yitong Chen, Haidong Cao, Shunlin Lu, Zuxuan Wu, Yu-Gang Jiang
Vision-language-action and world-action models have demonstrated impressive capabilities in robotics, yet generalization to unseen tasks remains challenging. More recently, general-purpose multimodal...
The paper introduces 2AM, a system that keeps task memory solely within a multimodal Agent while using a single RGB‑based, stateless Action Model to execute motions. By compiling interaction history into subtask language and optional 2D grasp/place/move hints, the Agent steers the Action Model, which is trained to tolerate imperfect guidance through dropout, noise, and jitter. On the LIBERO‑Mem benchmark, 2AM achieves 76.3% average completion without depth, geometry, or planners, vastly outperforming the best baseline.