architecture · first seen 8 Oct 2026
vision-language-action agents
Also: VLM agents, vision-language agent, vision-language-model agents
Models that map visual and language inputs to robot or embodied actions using pretrained vision-language models.
Mentions per week
PapersCodeDiscussion
Earliest sources
- ViSkill: Reinforcing VLM Agents with Evolving Visual-Native SkillsPapers · 8 Oct 2026 · Hongxing Li, Dingming Li, Yixin Li, Yong Du, Wenqi Zhang, Weiming Lu, Jun Xiao,…
- Look Before You Move: Agent-Interface-Aligned Supervision for Open-World Mobile ManipulationPapers · 11 Oct 2026 · Ronghe Qiu, Teli Ma, Jiaming Zhou, Zeying Gong, Yiting He, Qiang Huang, Junwei L…
- SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?Papers · 19 Oct 2026 · Zhaoxi Zhang, Hao Liang, Linxuan Wu, Yiming Xu, Yifu Yuan, Kun Liang, Chenming T…
- Pano2BIM: A Geometry-Constrained Vision-Language Agent for As-Built BIM Generation from a Floor Plan and a Single 360$^\circ$ ImagePapers · 25 Oct 2026 · Juan Diego Castaño Molina, Borja García de Soto
- Gym-Anything-RT: Scaling Real-Time Environments for Vision-Language AgentsPapers · 27 Oct 2026 · Pranjal Aggarwal, Sean Welleck
- GeoGuesser Bench: Benchmarking Vision-Language Agents on Interactive GeolocationPapers · 2 Nov 2026 · Huanzhi Mao, Yichuan Wang, Michael Koo, Wenyuan Huang, Huy Doan, Jinghan Xia, Zi…
Latest sources
- AgentCT: A Vision-Language Agent for Universal CT ImagingPapers · 8 Nov 2026 · Zhihao Chen, Qi Gao, Chuang Niu, Qiegen Liu, Yi Zhang, Hongming Shan
- GeoGuesser Bench: Benchmarking Vision-Language Agents on Interactive GeolocationPapers · 2 Nov 2026 · Huanzhi Mao, Yichuan Wang, Michael Koo, Wenyuan Huang, Huy Doan, Jinghan Xia, Zi…
- Gym-Anything-RT: Scaling Real-Time Environments for Vision-Language AgentsPapers · 27 Oct 2026 · Pranjal Aggarwal, Sean Welleck
- Pano2BIM: A Geometry-Constrained Vision-Language Agent for As-Built BIM Generation from a Floor Plan and a Single 360$^\circ$ ImagePapers · 25 Oct 2026 · Juan Diego Castaño Molina, Borja García de Soto
- SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?Papers · 19 Oct 2026 · Zhaoxi Zhang, Hao Liang, Linxuan Wu, Yiming Xu, Yifu Yuan, Kun Liang, Chenming T…
- Look Before You Move: Agent-Interface-Aligned Supervision for Open-World Mobile ManipulationPapers · 11 Oct 2026 · Ronghe Qiu, Teli Ma, Jiaming Zhou, Zeying Gong, Yiting He, Qiang Huang, Junwei L…
- ViSkill: Reinforcing VLM Agents with Evolving Visual-Native SkillsPapers · 8 Oct 2026 · Hongxing Li, Dingming Li, Yixin Li, Yong Du, Wenqi Zhang, Weiming Lu, Jun Xiao,…