English
Related papers

Related papers: Visual Agentic AI for Spatial Reasoning with a Dyn…

200 papers

We study the task of embodied visual active learning, where an agent is set to explore a 3d environment with the goal to acquire visual scene understanding by actively selecting views for which to request annotation. While accurate on some…

Computer Vision and Pattern Recognition · Computer Science 2020-12-18 David Nilsson , Aleksis Pirinen , Erik Gärtner , Cristian Sminchisescu

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…

Artificial Intelligence · Computer Science 2026-05-22 Mingkai Deng , Jinyu Hou , Lara Sá Neves , Varad Pimpalkhute , Taylor W. Killian , Zhengzhong Liu , Eric P. Xing

Multimodal Large Language Models (MLLMs) are evolving from passive observers into active agents, solving problems through Visual Expansion (invoking visual tools) and Knowledge Expansion (open-web search). However, existing evaluations fall…

Artificial Intelligence · Computer Science 2026-04-06 Qianshan Wei , Yishan Yang , Siyi Wang , Jinglin Chen , Binyu Wang , Jiaming Wang , Shuang Chen , Zechen Li , Yang Shi , Yuqi Tang , Weining Wang , Yi Yu , Chaoyou Fu , Qi Li , Yi-Fan Zhang

Visual Retrieval-Augmented Generation (VRAG) empowers Vision-Language Models to retrieve and reason over visually rich documents. To tackle complex queries requiring multi-step reasoning, agentic VRAG systems interleave reasoning with…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Yucheng Shen , Jiulong Wu , Jizhou Huang , Dawei Yin , Lingyong Yan , Min Cao

Vision-language models (VLMs) are essential to Embodied AI, enabling robots to perceive, reason, and act in complex environments. They also serve as the foundation for the recent Vision-Language-Action (VLA) models. Yet most evaluations of…

Spatiotemporal intelligence in autonomous driving (AD) requires an agent to integrate multi-view observations into a coherent scene representation, maintain object continuity across viewpoints and time, and reason about spatial relations,…

Spatial reasoning is an essential problem in embodied AI research. Efforts to enhance spatial reasoning abilities through supplementary spatial data and fine-tuning have proven limited and ineffective when addressing complex embodied tasks,…

Recently, large language models (LLMs) have demonstrated remarkable problem-solving capabilities by autonomously integrating with external tools for collaborative reasoning. However, due to the inherently complex and diverse nature of…

Artificial Intelligence · Computer Science 2025-11-03 Mengjie Deng , Guanting Dong , Zhicheng Dou

Vision-Language Models (VLMs) show promise for autonomous driving, yet their struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning. To overcome…

Visual spatial intelligence is critical for medical image interpretation, yet remains largely unexplored in Multimodal Large Language Models (MLLMs) for 3D imaging. This gap persists due to a systemic lack of datasets featuring structured…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Quoc-Huy Trinh , Xi Ding , Yang Liu , Zhenyue Qin , Xingjian Li , Gorkem Durak , Halil Ertugrul Aktas , Elif Keles , Ulas Bagci , Min Xu

We present a Collaborative Agent-Based Framework for Multi-Image Reasoning. Our approach tackles the challenge of interleaved multimodal reasoning across diverse datasets and task formats by employing a dual-agent system: a language-based…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Angelos Vlachos , Giorgos Filandrianos , Maria Lymperaiou , Nikolaos Spanos , Ilias Mitsouras , Vasileios Karampinis , Athanasios Voulodimos

Architecture views are essential for software architecture documentation, yet their manual creation is labor intensive and often leads to outdated artifacts. As systems grow in complexity, the automated generation of views from source code…

Software Engineering · Computer Science 2026-03-24 Miryala Sathvika , Rudra Dhar , Karthik Vaidhyanathan

While multimodal large language models (MLLMs) have made groundbreaking progress in embodied intelligence, they still face significant challenges in spatial reasoning for complex long-horizon tasks. To address this gap, we propose…

Achieving human-level intelligence requires refining cognitive distinctions between System 1 and System 2 thinking. While contemporary AI, driven by large language models, demonstrates human-like traits, it falls short of genuine cognition.…

Machine Learning · Computer Science 2025-02-11 Guangyan Sun , Mingyu Jin , Zhenting Wang , Cheng-Long Wang , Siqi Ma , Qifan Wang , Tong Geng , Ying Nian Wu , Yongfeng Zhang , Dongfang Liu

Recent advancements in Vision Language Models (VLMs) have expanded their capabilities to interactive agent tasks, yet existing benchmarks remain limited to single-agent or text-only environments. In contrast, real-world scenarios often…

Artificial Intelligence · Computer Science 2026-04-14 Zelai Xu , Zhexuan Xu , Xiangmin Yi , Huining Yuan , Mo Guang , Kaiwen Long , Xinlei Chen , Yi Wu , Chao Yu , Yu Wang

Video-based spatial cognition is vital for robotics and embodied AI but challenges current Vision-Language Models (VLMs). This paper makes two key contributions. First, we introduce ViCA (Visuospatial Cognitive Assistant)-322K, a diverse…

Computer Vision and Pattern Recognition · Computer Science 2025-09-10 Qi Feng

With the continuous expansion of Large Language Models (LLMs) and advances in reinforcement learning, LLMs have demonstrated exceptional reasoning capabilities, enabling them to address a wide range of complex problems. Inspired by these…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Hongrui Jia , Chaoya Jiang , Shikun Zhang , Wei Ye

Natural language provides a widely accessible and expressive interface for robotic agents. To understand language in complex environments, agents must reason about the full range of language inputs and their correspondence to the world.…

Computation and Language · Computer Science 2017-10-03 Stephanie Zhou , Alane Suhr , Yoav Artzi

Incremental decision making in real-world environments is one of the most challenging tasks in embodied artificial intelligence. One particularly demanding scenario is Vision and Language Navigation~(VLN) which requires visual and natural…

Artificial Intelligence · Computer Science 2024-01-25 Raphael Schumann , Wanrong Zhu , Weixi Feng , Tsu-Jui Fu , Stefan Riezler , William Yang Wang

Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in general vision-language tasks. However, recent studies have exposed critical limitations in their spatial reasoning capabilities. This deficiency in…

Machine Learning · Computer Science 2025-06-04 Huanyu Zhang , Chengzu Li , Wenshan Wu , Shaoguang Mao , Yifan Zhang , Haochen Tian , Ivan Vulić , Zhang Zhang , Liang Wang , Tieniu Tan , Furu Wei