paper-with-me

Papers

S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence

2026-06-18 · Yalun Dai, Hao Li, Shulin Tian, Runmao Yao, Yuhao Dong, Fangzhou Hong, Zhaoxi Chen, Fangfu Liu, Baoliang Tian, Dingwen Zhang, Tao Wang, Kim-Hui Yap, Ziwei Liu arxiv

Real-world spatial intelligence requires reasoning over a continuous and evolving 3D world, yet existing VLMs and tool-augmented agents largely remain tied to static, stateless inference from isolated visual observations. We introduce \textbf{\textsc{S-Agent}}, a spatial tool-use agentic paradigm for understanding and reasoning over continuous multi-view images and videos. By formulating spatial reasoning as spatio-temporal evidence accumulation rather than isolated frame-level prediction, \textsc{S-Agent} reshapes spatial perception into scene-centric understanding beyond frame-centric recognition. Specifically, \textsc{S-Agent} casts the VLM as a semantic planner that decides what evidence is needed, while a hierarchy of spatial tools and experts grounds objects in 2D, lifts them into 3D geometric evidence, and aggregates this evidence into high-level spatial knowledge (\textit{e.g.}, counting, measurement, orientation, and relative position). Additionally, a temporal memory mechanism, including Scene Memory for maintaining the evolving scene state and Agent Memory for accumulating reasoning context, enables evidence integration across frames and reasoning steps. Comprehensive experiments on multi-view and video spatial reasoning benchmarks show that \textsc{S-Agent} consistently improves both open-source and closed-source VLMs in a training-free manner. Beyond inference-time augmentation, supervised fine-tuning (SFT) on \textsc{S-Agent}-generated spatial trajectories \textsc{S-300K} yields \textsc{S-Agent-8B}, a compact spatial agent that significantly surpasses similar-scale baselines (e.g., Qwen3-VL-8B) and performs comparably to advanced closed-source models (e.g., GPT-5.4 and Gemini 3).

📄 PDF Abstract BibTeX arXiv:2606.20515

Code (0)

등록된 구현이 없습니다.

Tasks

Spatial Reasoning

Similar Papers 제목 키워드 기반

ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models

2026-05-11 · Tingshu Mou, Jiabo He, Renying Wang, Ce Liu 외 arxiv

Recent advances in Multi-modal Large Language Models (MLLMs) target 3D spatial intelligence, yet the progress has been largely driven by post-training on curated benchmarks, leaving the inference-time approach relatively…

Spatial Reasoning

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text

2026-07-23 · Xu Wang, Kaixiang Yao, Miao Pan, Xiaohe Zhou 외 arxiv

Spatial intelligence is essential for agents to move from static semantic understanding toward interacting with the physical world. Many spatial tasks are grounded in continuous visual scenes, where locations, regions, a…

Spatial Reasoning

MapAgent: A Hierarchical Agent for Geospatial Reasoning with Dynamic Map Tool Integration

2025-09-07 · Md Hasebul Hasan, Mahir Labib Dihan, Tanzima Hashem, Mohammed Eunus Ali 외 arxiv

Agentic AI has significantly extended the capabilities of large language models (LLMs) by enabling complex reasoning and tool use. However, most existing frameworks are tailored to domains such as mathematics, coding, or…

Spatial Reasoning

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

2026-06-11 · Seokju Cho, Ryo Hachiuma, Abhishek Badki, Hang Su 외 arxiv

Spatial reasoning, the ability to determine where objects are, how they relate, and how they move in 3D, remains a fundamental challenge for vision-language models (VLMs). Tool-augmented agents attempt to address this by…

Spatial Reasoning

Technical Report of RoboSpatial Challenge at CVPR 2026: Selective Reasoning Activation and Reference-Frame Disambiguation for Embodied Spatial Reasoning

2026-06-30 · Yuxiang Xie, Qi Lv, Jianming Xing, Zijian Hong 외 arxiv

Vision-language models achieve strong general perception but often struggle with the spatial reasoning required for embodied tasks. We present RoboSpatialBrain, our submission to the RoboSpatial Challenge at the Embodied…

Spatial Reasoning