Embodied AI

Ask about this topic

Overview

Embodied AI asks how agents can connect perception and reasoning to actions that change a physical or simulated world. Common approaches include vision-language-action models, language-model agents with tools and hierarchical plans, reinforcement learning, persistent spatial or episodic memory, and world models trained with robot demonstrations or generated simulation data. Researchers evaluate these systems on navigation, manipulation, household tasks, and multi-agent coordination, using benchmarks as well as real robots. A central challenge is that strong perception or short-task scores do not guarantee reliable long-horizon behavior: agents still struggle with physical constraints, changing conditions, recovery, and safety, while simulated success may not transfer to deployment.

Latest papers

CardsList

255 papers28 papers in the last four weeks, down 15% on the four weeks before. 0.2% of all new papers.

  1. OmniBrain-0: A Unified Agentic Model for Embodied Intelligence

    Oct 26, 2026Xiaomi Embodied Intelligence Team, Yuechen Luo, Chong He +29Embodied AIAgentic AI for Robotics

    University of Macau × Tsinghua University · University of Macau, Tsinghua University

  2. Know When to Escalate: Critic-Guided Adaptive Execution for Cloud-Local Embodied Agents

    Oct 22, 2026Wei Zhang, Lirong Xiang, Charles FlemingEmbodied AIAdaptive Model Routing

    University of Illinois Urbana-Champaign · Cornell University · Cisco

  3. Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use

    Oct 21, 2026Yanzhe Chen, Ziyi Yang, Jifeng Zhu +14Multimodal AgentsEmbodied AI

    Show Lab, National University of Singapore

  4. CAPSafe: A Benchmark for Contextual Action and Plan Safety Reasoning in Embodied Agents

    Oct 20, 2026Youmna Farag, Svetlana Stoyanchev, Simon Keizer +2AI Agent SafetyAI Agent Safety Benchmarks

    Cambridge Research Laboratory, Toshiba Europe Ltd, Cambridge, UK

  5. Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds

    Oct 20, 2026Kuan Zhang, Yukun Chen, Zhihao Yang +8Embodied AIContinued Pretraining

    miHoYo Honkai AI R&D Team · College AI, Tsinghua University · University of Chinese Academy of Sciences +3

  6. VEOcc++: Learning Persistent Voxel Feature Maps for Embodied Online Semantic Occupancy Mapping and Offline Refinement

    Oct 20, 2026Ruoyu Wang, Jiahan Li, Yong Liu +1Semantic Occupancy Mapping3D Mapping

    APRIL Lab, Institute of Cyber-Systems and Control, Zhejiang University, China

  7. Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy

    Oct 19, 2026Zekai Li, Jiayi Yu, Jinlu Zhang +8Self-Improving AgentsEmbodied AI

    Galbot Team

  8. Multimodal Filesystem Memory For Long-Horizon Embodied Agents

    Oct 15, 2026Chloe Su, Jiahan Li, Zhenting Qi +5Agent MemoryLong-Term Memory for Embodied Agents

  9. Has GPT-6-Astra Achieved Embodied Intelligence?

    Oct 15, 2026SenseNova, Joint Research Team, Zhongang Cai +59Embodied AIAgentic AI for Robotics

  10. OnBodyAI - Why the Next AI Needs a Body

    Oct 15, 2026Michael BeiglEmbodied AIHuman-Centered AI

    Karlsruhe Institute of Technology (KIT), Germany

  11. HelpMeOut: A Neuropsychology-Grounded Benchmark for Error-Aware Monitoring of Household Task Execution

    Oct 13, 2026Haoran Wang, Jingwei Huang, Anqing Duan +2AI Agent MonitoringAI Agent Benchmarks

    University of Auckland, New Zealand · MBZUAI, United Arab Emirates

  12. Proactive Physical AI through Continuous Observation and Timely Intervention

    Oct 12, 2026Zhenhua Yang, Jiafeng Liang, Xingyu Zhou +26Proactive AgentsEmbodied AI

    Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology · Guanxing Technology

  13. Embodied Skill Bench: Benchmarking How Well Agents with Embodied Skills Perform on Physical Tasks

    Oct 12, 2026Zhi Han, Zihan Guo, Chenxi Zeng +6Embodied Agent BenchmarksEmbodied AI

    Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · Sun Yat-Sen University +2

  14. Sensing via whole-body interactions with complex terrains: physical insights from robotic models

    Oct 11, 2026Chen LiBioinspired RoboticsRobotics

    Department of Mechanical Engineering, Johns Hopkins University, Baltimore, MD 21218, USA

  15. EnactOpt: Diagnosis-Guided Harness Evolution for Embodied Agents

    Oct 10, 2026ZhiYuan Feng, Zhuoshi Pan, Zhaolu Kang +5Agent Harness OptimizationEmbodied AI

    Tsinghua University · Peking University · Kling AI +1

  16. StateSkill-Agent: An Effective and Efficient Embodied Agent via State-conditioned Skill

    Oct 10, 2026Changxu Wei, Jingyi Zhang, Zhiyu Zheng +6Finite-State MachineLLM Agent Skill Learning

    The Hong Kong Polytechnic University · ACE Robotics · Nanyang Technological University +3

  17. MAGMA-Bench: Evaluating Long-Horizon Embodied Agents under Dynamic Tasks and Execution Failures

    Oct 9, 2026Loan Bernat, Matthieu Grard, Ariane Herbulot +1Embodied Agent BenchmarksLong-Horizon Agent Evaluation

    LAAS-GEPETTO · LAAS-RAP

  18. What Should Embodied Agents Remember? Benchmarking and Evaluating Memory Modality for Embodied Agents

    Oct 8, 2026Junxiang Wang, Yuchen Liu, Yi Wu +6Long-Term Memory for Embodied AgentsAgent Memory

    Dexmate · Carnegie Mellon University · Purdue University

  19. EMHO: EMbodied Agent Harness Optimization via Experience Traces

    Oct 6, 2026Hyun Jung Lee, Jungtaek Kim, Jongwon Jeong +3Agent Harness OptimizationEmbodied AI

    Korea University · University of Arkansas · University of Wisconsin–Madison

  20. Toward Trustworthy Physical AI for Human Interaction

    Oct 5, 2026Niccolò Pagliarani, Maximilian Stölzle, Cosima du Pasquier +6RoboticsRobot Safety

    The BioRobotics Institute, Scuola Superiore Sant’Anna, Pontedera, Italy. · CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA. · CHARM Lab, Stanford University, Stanford, CA, USA. +3

  21. Is this machine playing?

    Oct 5, 2026Nathan Cloos, Antonio Norelli, Daniel Durbin +3Agent Skill LearningSelf-Improving Agents

    MIT

  22. Inspect Robots: Evaluating the Capabilities and Safety of Embodied AI

    Oct 5, 2026Christopher Leet, Achu Menon, Sravanthi Machcha +12Robot SafetyAI Agent Evaluation

    Robocurve · University of Southern California · San Jose State University +7

  23. EnvDreamer: Large-Scale Multimodal-to-Environment Generation for Embodied AI

    Oct 3, 2026Kabir Swain, Sijie Han, Antonio TorralbaSynthetic Data Generation for Robotics3D Scene Generation

    MIT · University of Toronto

  24. On Representational Alignment among Embodied Agents

    Oct 2, 2026Fulvio MastrogiovanniRepresentation AlignmentEmbodied AI

    University of Genoa, Italy

  25. Joint Movement and Compression Ratio Design for Mobile Embodied AI Networks (MEAN)

    Oct 1, 2026Yahao Ding, Jiaxiang Wang, Zhouxiang Zhao +3Wireless CommunicationsWireless Resource Allocation

    King’s College London · Zhejiang University · University of Miami

  26. Token Communication-Assisted Collaborative Embodied Artificial Intelligence: Concepts, Framework, and Opportunities

    Oct 1, 2026Peng Yi, Ying-Chang LiangAgent Communication ProtocolsTask-Oriented Semantic Communication

    National Key Laboratory of Wireless Communications, and also with the Center for Intelligent Networking and Communications (CINC), University of Electronic Science and Technology of China (UESTC), Chengdu 611731, China · Institute of Fundamental and Frontier Sciences and the Center for Intelligent Networking and Communications (CINC), University of Electronic Science and Technology of China (UESTC), Chengdu 611731, China

  27. Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena

    Oct 1, 2026Haojian Huang, Pukun Zhao, Zexi Li +7VLM EvaluationVisual Reasoning

    HKUST (GZ) · Knowin AI · The Chinese University of Hong Kong

  28. LIBERO-Agent: Evaluating General-Purpose Agents for Direct Embodied Manipulation

    Sep 30, 2026Zijie Diao, Yitong Chen, Sicheng Xie +7Long-Horizon Robotic ManipulationContact-Rich Robotic Manipulation

    Institute of Trustworthy Embodied AI, Fudan University · Shanghai Innovation Institute

  29. Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence

    Sep 28, 2026Hongcheng Gao, Jingjing Zhou, Zelin Zheng +10AI Coding AgentsLarge Language Model-Based Robot Planning

  30. REALM: A Coarse-to-Fine Generative Framework for Embodied Reactive Listening

    Sep 27, 2026Peizhen Li, Longbing Cao, Yang ZhangAudio-Driven Facial AnimationFacial Expression Synthesis

    Macquarie University, Australia · University of North Texas, USA