arXiv Computer Vision October 9, 2026 By Jinkai Zhang, Jingyi Xu, Yuanhong Yu, Jiarui Guo, Ruizhen Hu, Hujun Bao, Xiaowei Zhou, Sida Peng

SuperNav: An Agentic Navigation System for Any Task in Any Scene

Read the original on arXiv Computer Vision →

SuperNav is a navigation system that leverages a pretrained multimodal large language model (MLLM) without fine‑tuning it for navigation. The system introduces an agent harness that delegates motion execution to navigation tools while the MLLM focuses on interpreting requests, understanding scenes, and making decisions. A visual‑point interface connects the model’s decisions to motion, allowing direct destination specification and feedback‑driven revision, enabling sustained navigation across varied tasks and environments.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Oct 2

UrbanVLA: A Vision-Language-Action Model for Urban Micromobility

UrbanVLA is a Vision‑Language‑Action framework designed to enable delivery robots to navigate large‑scale urban environments using long‑horizon route instructions. The model aligns noisy route waypoints with visual observations and plans trajectories, trained through a two‑stage pipeline of supervised fine‑tuning on simulated data and reinforcement fine‑tuning on mixed simulation and real‑world data. Experiments show UrbanVLA outperforms strong baselines by over 55% on the SocialNav task and demonstrates reliable real‑world navigation in large urban settings.

By Anqi Li, Zhiyong Wang, Jiazhao Zhang, Minghan Li, Yunpeng Qi, Zhibo Chen, Zhizheng Zhang, He Wang

robotics fine-tuning multimodal safety

arXiv Computer Vision

5d ago

Agentic Scene Policies

arXiv:2509.19571v2 Announce Type: replace-cross Abstract: Designing or learning robot policies that generalize zero-shot across a range of language instructions and objects is a core problem in robot...

By Sacha Morin, Kumaraditya Gupta, Mahtab Sandhu, Charlie Gauthier, Francesco Argenziano, Kirsty Ellis, Liam Paull

llms agents robotics multimodal

arXiv AI

Aug 17

Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use

arXiv:2608. 14047v1 Announce Type: cross Abstract: This paper integrates end-to-end Visual-Language-Action (VLA) models with agentic tool-use to propose Agentic Robot with Tool-use (ART).

By Yi Ding, Yanzhao Yu, Xili Dai, Xianbiao Qi, Peiwen Sun, Xueqian Wang, Xiangyu Yue, Jianan Wang

agents robotics multimodal

arXiv AI

Sep 1

LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation

arXiv:2608.30935v1 Announce Type: cross Abstract: Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embod...

By Shaoan Wang, Aocheng Luo, Fei Huang, Jingyi Xu, Xiaoyang Wang, Yueyu Wang, Qianli Ma, Fan Yang, Ran Mei, Jia Wei, Jiangpeng Hu, Xuhao Liu, Hongming Chen, Yuanbin Shao, Yiyang Lin, Ziliang Li, Liang Pan, Xinhang Liu, Yuntao Ma, Tingxiang Fan

llms agents nlp reinforcement-learning robotics fine-tuning efficiency multimodal benchmarks

arXiv Machine Learning

Jul 1

ViTL: Temporal Logic-Guided Zero-Shot Natural Language Navigation via Vision-Language Models

arXiv:2606. 30696v1 Announce Type: cross Abstract: Enabling robots to follow natural language commands to complete zero-shot long-horizon tasks remains challenging.

By Kaier Liang, Hengde Dai, Cristian-Ioan Vasile

llms robotics multimodal

arXiv AI

Jul 14

Think When It Matters: Conditional VLM Reasoning for Social Navigation with RL Policies

arXiv:2607. 10991v1 Announce Type: cross Abstract: As mobile robots become more integrated into everyday human environments, social robot navigation is becoming essential for ensuring human comfort, safety, and trust.

By Ali Ahmadi, Hamed Rahimi, Adrien Jacquet Cretides, Marie Samson, Mahdi Khoramshahi, Mohamed Chetouani

llms reinforcement-learning robotics multimodal benchmarks safety

One email a morning, machine-written

Related stories

UrbanVLA: A Vision-Language-Action Model for Urban Micromobility

Agentic Scene Policies

Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use

LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation

ViTL: Temporal Logic-Guided Zero-Shot Natural Language Navigation via Vision-Language Models

Think When It Matters: Conditional VLM Reasoning for Social Navigation with RL Policies