Agentic AI for Robotics

Latest papers

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

ASPIRE: Agentic /Skills Discovery for Robotics
Jun 30, 2026Runyu Lu, Yubo Wu, Ethan Kou +11Robot Policy Learning Long-Horizon Robotic Manipulation
NVIDIA · UMich · UIUC +2
SPINE: Bridging the Cyber-Physical Gap with Agentic AI
Jun 29, 2026Minkyu Ham, Dongho Kim, Chan Lee +4Agentic AI for Robotics Robot Teleoperation
Department of Statistics and Data Science, Northwestern University · Department of Computer Science, Northwestern University
RHO: Your Coding Agent is Secretly a Roboticist
Jun 15, 2026Karim Elmaaroufi, Justin Svegliato, Sarunas Kalade +3LLM Agent Harnesses Robotic Manipulation
University of California, Berkeley · Embodied Science · AMD
SR-Platform: An Agentic Pipeline for Natural Language-Driven Robot Simulation Environment Synthesis
May 14, 2026Ben Wei Lim, Minh Duc Le, Thang Truong +13D Asset Generation Robotics Simulation
Strike Robotics
Nautilus: From One Prompt to Plug-and-Play Robot Learning
May 12, 2026Yufeng Jin, Jianfei Guo, Xiaogang Jia +8Robotic Policy Evaluation Agentic Code Generation
1TU Darmstadt · 6Independent Researcher · 2KIT +3
RACAS: Controlling Diverse Robots With a Single Agentic System
Mar 5, 2026Dylan R. Ashley, Jan Przepióra, Yimeng Chen +5Agentic AI for Robotics Robotic Control
Center of Excellence in Generative AI, King Abdullah University of Science and Technology (KAUST), Saudi Arabia. · Dalle Molle Institute for Artificial Intelligence Research (IDSIA), Switzerland. · Università della Svizzera italiana (USI), Switzerland. +3
MistyPilot: An Agentic Fast-Slow Thinking LLM Framework for Misty Social Robots
Mar 4, 2026Xiao Wang, Lu Dong, Jingchen Sun +3Agentic AI for Robotics LLM Agent Orchestration
State University of New York at Buffalo, Buffalo, NY 14260, USA
Demonstration-Free Robotic Control via LLM Agents
Jan 28, 2026Brian Y. Tsui, Alan Y. Fang, Tiffany J. HwuRobotic Control Language Model-Based Control
All authors are independent researchers.
Debate2Create: Robot Co-design via Multi-Agent LLM Debate
Oct 29, 2025Kevin Qiu, Marek CyganRobot Morphology-Control Co-Design Multi-Agent Debate
University of Warsaw · 2IDEAS NCBR · 3Nomagic

Jun 30, 2026J/K move · Enter open · S save

ASPIRE: Agentic /Skills Discovery for Robotics

Runyu Lu, Yubo Wu, Ethan Kou, Letian Fu+10

NVIDIA · UMich · UIUC+2

Robot Policy Learning Long-Horizon Robotic Manipulation Continual Robot Learning Robot Skill Learning Multi-Task Robotic Manipulation AI Control+7

Open paper AskPDF arXiv

Traditional robot programming is challenging: it requires orchestrating multimodal perception, managing physical contact dynamics, and handling diverse configurations and execution failures. We introduce ASPIRE (Agentic Skill Programming through Iterative Robot Exploration), a continual learning system that autonomously writes and refines robot control programs in a code-as-policy paradigm while compounding experience into a reusable skill library. ASPIRE discovers skills that persist across tasks, simulation and real-world settings, and embodiments. It operates in an open-ended loop with three components: (1) a closed-loop robot execution engine that exposes fine-grained multimodal traces, enabling autonomous failure diagnosis, repair synthesis, and validation; (2) a continually expanding skill library that distills validated fixes into reusable, transferable knowledge; and (3) evolutionary search that generates diverse task sequences and control programs to explore beyond single-trajectory refinement. ASPIRE surpasses prior methods by up to 77% on LIBERO-Pro manipulation under perturbation, 72% on Robosuite bimanual handover, and 32% on BEHAVIOR-1K long-horizon household tasks. Its accumulated library also enables zero-shot generalization to unseen long-horizon tasks: on LIBERO-Pro Long, ASPIRE achieves 31% success versus 4% for prior methods despite their use of test-time reasoning and retries. Finally, simulation-discovered skills provide initial evidence of sim-to-real transfer, substantially reducing real-robot programming effort across different embodiments and robot APIs.