Agentic AI for Robotics

Follow this topic Ask about this topic

Latest papers

39 papers13 papers in the last four weeks, up 333% on the four weeks before. 0.1% of all new papers.

HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents
Oct 16, 2026Hongcheng Gao, Alex Zhou, Jay Zhu +13Agentic AI for Robotics Code Generation for Robotics
InstAgent: A Recursively Self-Improving Agent Operating System for Heterogeneous Robot Collaboration
Oct 16, 2026Haoyang Luo, Junhao Qin, Jingyan Cao +7Agentic AI for Robotics Multi-Robot Systems
ShanghaiTech University, Shanghai, China. · InstAdapt, Shanghai, China.
Has GPT-6-Astra Achieved Embodied Intelligence?
Oct 15, 2026SenseNova, Joint Research Team, : +60Embodied AI Agentic AI for Robotics
Towards Agentic Robots: Model, Data, Environment, and Harness
Oct 14, 2026Chonghan Qin, Dongming Wu, Kaituo Feng +13Agentic AI for Robotics Robotics
Cracking Mobile Manipulation: From Failure Diagnosis to Agentic Robot System
Oct 14, 2026Zixuan Wang, Jia-Ning Li, Yinzhou Tang +5Agentic AI for Robotics Mobile Manipulation
School of Intelligence Science and Technology, Peking University · State Key Laboratory of General Artificial Intelligence, Peking University · Alibaba DAMO Academy, Alibaba Group +4
ChunkAct: Action Chunking for Agentic Robotics
Oct 13, 2026Bingxin Xu, Wenrui Bao, Xinxin Liu +3Agentic AI for Robotics Robotics
University of Southern California · University of Central Florida · Stony Brook University
SEAR: Self-Evolving Agentic Robotics
Oct 13, 2026Xinyi Wang, Bangzheng Li, Hanyu Wang +5Agentic AI for Robotics Robot Learning
Luma AI
Agentic Robot Creation through Generation, Verification, and Revision
Oct 13, 2026Xuebing Li, Yibo He, Sitong Liu +2Agentic AI for Robotics Robotics
ShanghaiTech University
SuperNav: An Agentic Navigation System for Any Task in Any Scene
Oct 8, 2026Jinkai Zhang, Jingyi Xu, Yuanhong Yu +5Robot Navigation Visual Robot Navigation
Zhejiang University · Shenzhen University · Causa Robotics
iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains
Oct 7, 2026Vincenzo Guarino, Emanuele Musumeci, Vincenzo Suriani +1Open-Vocabulary Semantic Mapping Agentic AI for Robotics
Department of Computer, Control and Management Engineering “Antonio Ruberti”, Sapienza University of Rome, Via Ariosto 25, 00185 Rome, Italy
Inspect Robots: Evaluating the Capabilities and Safety of Embodied AI
Oct 5, 2026Christopher Leet, Achu Menon, Sravanthi Machcha +12Robot Safety AI Agent Evaluation
Robocurve · University of Southern California · San Jose State University +7
Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation
Oct 2, 2026Xincheng He, Siyu Ma, Chang Yu +5Robot Skill Learning Sim-to-Real Transfer
University of California, Los Angeles · Shanghai Jiao Tong University · University of Utah +1
OpenRUA: Robot-Use Agents Are Zero-Shot Visuomotor Policies
Oct 1, 2026Zhaoyang Chu, Earl T. Barr, Claire Le Goues +4Agentic AI for Robotics Zero-Shot Robotic Manipulation
University College London · Carnegie Mellon University
Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents
Oct 1, 2026Yen-Jen Wang, Haozhe Jiang, Shuying Deng +7Robot Skill Learning Large Language Model-Based Robot Planning
UC Berkeley · Amazon FAR · MIT +1
Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens
Oct 1, 2026Ruiyang Si, Jianxin Bi, Shunyu Yang +12Vision-Language-Action Models Tool-Augmented Language Model Agents
Peking University · National University of Singapore · NVIDIA +1
Make Code as Policy Great Again: Frontier Agents Write, Call, and Evolve Robot Tools
Sep 30, 2026Shijia Ge, Alex Zhou, Jianshu Zeng +12Robotic Tool Use Tool-Using Agents
Hexafuture Inc. · Peking University · Beijing Institute of Technology +1
Encore: Few-Shot Agentic Discovery of Manipulation Strategies
Sep 29, 2026Yifan Kang, Zihan Wang, Zhiwen Fan +1Robot Policy Learning Language-Conditioned Robot Manipulation
Massachusetts Institute of Technology · AI Open Source Foundation · Texas A&M University +1
RoboHarness: A Simple Harness Outperforms VLA and World Action Models
Sep 29, 2026Bince Qu, Wei Chen, Bo ZhangAgentic AI for Robotics LLM Agent Harnesses
Zhejiang University
AGRO-SUVIDE: Agentic Robotics for Surgical Viscoelastic Debridement
Sep 28, 2026Shutong Jin, Ziyang Chen, Preethi Satish +4Robot Skill Learning Agentic AI for Robotics
Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, USA. · Department of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, SE 10044, Sweden. · Intuitive Surgical, Sunnyvale, CA 94086, USA.
RAPID: Robot Agentic Programming from Demonstrations
Sep 24, 2026Yuyao Liu, Jiayuan Mao, David Hsu +2Program Synthesis Contact-Rich Robotic Manipulation
Massachusetts Institute of Technology · National University of Singapore · University of Pennsylvania +1
Robo-Harness K1: Harnessing Robot-Use Agents via Perception Augmentation
Sep 24, 2026Zexi Li, Yehang Zhang, Wenqian Li +12Language-Conditioned Robot Manipulation Agentic AI for Robotics
The Chinese University of Hong Kong · Knowin AI · The Hong Kong University of Science and Technology (Guangzhou)
Show-Harness: Just a VLM Agent Can Play Robots
Sep 9, 2026Yanzhe Chen, Zechen Bai, Zhijun Cao +7Cross-Embodiment Robot Learning Language-Conditioned Robot Control
Show Lab, National University of Singapore
Physical Agentic AI: An Architecture for Orchestrating a Robot Crew with LLMs
Aug 23, 2026Xinyuan Liu, Eren Sadikoglu, Riana Chatterjee +1Agentic AI for Robotics LLM Agent Orchestration
School of Computing and Augmented Intelligence, Arizona State University, AZ, USA
Revisiting the "Push-T" Robot Manipulation Task with Agentic Robotics
Aug 18, 2026Shuangyu Xie, Kaiyuan Chen, Ken GoldbergAgentic AI for Robotics Robotics
University of California, Berkeley
MistyPilot: Enabling Social-Robot Control through Multi-Agent LLM Skill Orchestration
Aug 16, 2026Xiao Wang, Lu Dong, Ifeoma Nwogu +2Agentic AI for Robotics LLM Agent Orchestration
State University of New York at Buffalo
ETA: A New Agentic Paradigm for Embodied Tasks
Aug 4, 2026Yitong Chen, Zezheng Huai, Sixian Li +7Tool-Using Agents Robot Task Planning
1Shanghai Innovation Institute · 2Fudan University · 3Jilin University +2
You Don't Need To Stay in The Loop: An Agentic Robotics Loop for Robot-Policy Improvement
Aug 2, 2026Hang YuRobot Policy Adaptation Agentic AI for Robotics
Independent Researcher, United States.
Addressing the Orchestration Gap in Generalist Robots via Physical Agency
Jul 23, 2026Liane Galanti, Dhruv Shah, Tri DaoRobotic Manipulation Robot Task Planning
1Princeton University · 2Together AI
VIA: Visual Interface Agent for Robot Control
Jul 13, 2026Hengyuan Hu, Jensen Gao, Priya Sundaresan +3Robotic Control Zero-Shot Robotic Manipulation
Stanford University
ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI
Jul 5, 2026ACE-Brain Team, :, Ziyang Gong +29Robot Foundation Models Model Merging
ACE-Brain Team

Oct 16, 2026J/K move · Enter open · S save

HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents

Hongcheng Gao, Alex Zhou, Jay Zhu, Zelin Zheng+12

Agentic AI for Robotics Code Generation for Robotics Coding Agents LLM Agent Harnesses Robot Manipulation Benchmarks

Open paper AskPDF arXiv

Agents built on vision language models (VLMs) now compete with learned policies on robot manipulation leaderboards. We ask how far a coding agent can go when it controls a robot instead of a computer, and where it stops. Our system, HexaShell, keeps the harness thin: it only turns the agent's commands into robot motion. The agent drives a robot with two arms through one command line. It sees three RGB cameras and knows their calibration. After each failed attempt, the agent reads the log, finds the cause, and writes or fixes small programs called tools. In this way it keeps what it learns as code, as a coding agent does when it fixes a failing test. The tools may use only what the robot observes. They use triangulation to find where objects are, relative to each other and to the gripper. If two cameras see the same point, the point lies where the two camera rays meet. If a point lies on a known plane, such as the table or the top of a block, it lies where its ray meets that plane. When the head camera is not enough, the robot moves a wrist camera to get a second view. We build the tools on only ten layouts of one seed per task, then freeze them and test them on ten new layouts of the same seed. We use Codex with GPT-6-Astra at medium reasoning effort. On all 42 RoboDojo tasks, HexaShell reaches a success rate of 39.7% and a progress score of 48.0, averaged in the same way as the leaderboard. This is a new state of the art on RoboDojo. The limit is contact, not reasoning: pushing reaches 92.5% and memory tasks 65.0%, but tight insertion only 8.3%. When the agent fails, it usually sees the failure but cannot make the motion work. We open source the tools evolved so far at https://github.com/HexaFuture/HexaShell.