Full-text records with permanent local identifiers are available in the paper archive .
2026 Where the Harness Meets the Physical World: A Survey of the Physical Agentic Harness
Chenxi Zeng, Zihan Guo, Zicai Cui, and 15 more authors
Preprint , Oct 2026
Embodied foundation models now allow robots to act on open-ended instructions, yet success on long-horizon physical tasks also depends on the runtime around the model, which organizes the task, invokes skills, guards execution, and retains experience. This survey defines the physical agentic harness as a research object and reviews over 200 works through six functional responsibilities: task orchestration, digital resources, embodied capabilities, execution governance, digital-physical interaction, and persistent evolution.
@article { zeng2026physicalharness ,
title = {Where the Harness Meets the Physical World: A Survey of the Physical Agentic Harness} ,
author = {Zeng, Chenxi and Guo, Zihan and Cui, Zicai and Tang, Yang and Xin, Yue and Han, Zhi and Yuan, Yuan and Yang, Liuhaichen and Zhang, Shao and Zhang, Chen and Wu, Chao and Jiang, Bingqi and Zhang, Jingjing and Zhou, Dongzhan and Hu, Shuyue and Zhou, Ming and Zhang, Weinan and Li, Yang} ,
journal = {Preprint} ,
year = {2026} ,
month = oct ,
} SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution
Zhi Han, Chenxi Zeng, Liuhaichen Yang, and 3 more authors
arXiv preprint arXiv:2608.05573 , Oct 2026
Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration
Zihan Guo, Zeyi Chen, Zhiyu Chen, and 15 more authors
arXiv preprint arXiv:2606.30246 , Oct 2026
InternLab: A Governed Network of Physically Intelligent Autonomous Laboratories for Open-world Scientific Discovery
Yang Li , Ming Zhou, Dongzhan Zhou, and 51 more authors
Unpublished , Oct 2026
CoNav-UAV: Cooperative Dual-Altitude Aerial Navigation via Stackelberg Learning
Junru Song, Wenhao Zhang, Yang Yang, and 7 more authors
arXiv preprint arXiv:2608.01802 , Oct 2026
DF^3: World Modeling via Decoder-Free Feature Forecasting in Autonomous Navigation
Jiaming Chen, Guoan Xu, Aoshen Huang, and 3 more authors
arXiv preprint arXiv:2608.02428 , Oct 2026
Multi-Robot Open Adaptive Teaming Across Unseen Environments, Partners, and Scales
Yang Li , Feng Xue, Fan Mo, and 6 more authors
arXiv preprint arXiv:2607.04972 , Oct 2026
Under Review Position: Autonomous Scientific Discovery Needs Embodied Experimentation with Learnability
Yihang Chen, Zhongwei Yu, Yang Li , and 4 more authors
TechRxiv , Oct 2026
PEPA: a Persistently Autonomous Embodied Agent with Personalities
Kaige Liu, Yang Li , Lijun Zhu, and 1 more author
arXiv preprint arXiv:2603.00117 , Oct 2026
VLM-SFD: VLM-Assisted Siamese Flow Diffusion Framework for Dual-Arm Cooperative Manipulation
Jiaming Chen, Yiyu Jiang, Aoshen Huang, and 2 more authors
IEEE Robotics and Automation Letters , Oct 2026
2025 Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning
Yang Li , Zhiyuan He, Yuxuan Huang, and 5 more authors
arXiv preprint arXiv:2511.23262 , Oct 2025
AT-Drone: Benchmarking Adaptive Teaming in Multi-Drone Pursuit
Yang Li , Junfan Chen, Feng Xue, and 5 more authors
arXiv preprint arXiv:2502.09762 , Oct 2025
2024 Aligning Individual and Collective Objectives in Multi-Agent Cooperation
Yang Li , Wenhao Zhang, Jianhong Wang, and 4 more authors
arXiv preprint arXiv:2402.12416 , Oct 2024
JAIR Tackling Cooperative Incompatibility for Zero-Shot Human-AI Coordination
Yang Li , Shao Zhang, Jichen Sun, and 5 more authors
Journal of Artificial Intelligence Research , Oct 2024
Under Review HOLA-Drone: Hypergraphic Open-ended Learning for Zero-Shot Multi-Drone Cooperative Pursuit
Yang Li , Dengyu Zhang, Junfan Chen, and 3 more authors
Cross-Utterance Conditioned VAE for Speech Generation
Yang Li , Cheng Yu, Guangzhi Sun, and 7 more authors
In , Oct 2024
ICML Open Ad Hoc Teamwork with Cooperative Game Theory
Jianhong Wang, Yang Li , Yuan Zhang, and 2 more authors
arXiv preprint arXiv:2402.15259 , Oct 2024
ICML Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning
Tenglong Liu, Yang Li , Yixing Lan, and 3 more authors
arXiv preprint arXiv:2405.19909 , Oct 2024
2023 ICML Cooperative Open-ended Learning Framework for Zero-shot Coordination
Yang Li , Shao Zhang, Jichen Sun, and 4 more authors
In Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20470-20484, 2023. , Oct 2023
TMLR JiangJun: Mastering Xiangqi by Tackling Non-Transitivity in Two-Player Zero-Sum Games
Yang Li , Kun Xiong, Yingping Zhang, and 6 more authors
Transactions on Machine Learning Research , Oct 2023
IEEE TMC Self-Supervised MAFENN for Classifying Low-labeled Distorted Images over Mobile Fading Channels
Yang Li , Fanglei Sun, Jingchen Hu, and 8 more authors
IEEE Transactions on Mobile Computing , Oct 2023
Under Review Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach
Bin Zhang, Hangyu Mao, Jingqing Ruan, and 8 more authors
arXiv preprint arXiv:2311.13884 , Oct 2023
Cross-utterance Conditioned Coherent Speech Editing
Cheng Yu, Yang Li , Weiqin Zu, and 3 more authors
In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH , Oct 2023
2022 ACL Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech
Yang Li , Cheng Yu, Guangzhi Sun, and 6 more authors
In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , Oct 2022
Multi-Agent Feedback Enabled Neural Networks for Intelligent Communications
Fanglei Sun, Yang Li , Ying Wen, and 4 more authors
IEEE Transactions on Wireless Communications , Oct 2022
2021 ICLR Ligs: Learnable intrinsic-reward generation selection for multi-agent learning
David Henry Mguni, Taher Jafferjee, Jianhong Wang, and 7 more authors
arXiv preprint arXiv:2112.02618 , Oct 2021
MAFENN: Multi-agent feedback enabled neural network for wireless channel equalization
Yang Li , Fanglei Sun, Weiqin Zu, and 6 more authors
In 2021 IEEE Global Communications Conference (GLOBECOM) , Oct 2021
Retrospective thinking based multi-agent system for wireless video transmissions
Yang Li , Fanglei Sun, Wenbin Song, and 4 more authors
In ICC 2021-IEEE International Conference on Communications , Oct 2021
2018 High quality depth estimation from monocular images based on depth prediction and enhancement sub-networks
Xiangyue Duan, Xinchen Ye, Yang Li , and 1 more author
In 2018 IEEE international conference on multimedia and expo (ICME) , Oct 2018
Position: Autonomous Scientific Discovery Needs Embodied Experimentation with LearnabilityTechRxiv, Oct 2026
HOLA-Drone: Hypergraphic Open-ended Learning for Zero-Shot Multi-Drone Cooperative PursuitOct 2024
Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic ApproacharXiv preprint arXiv:2311.13884, Oct 2023
Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-SpeechIn Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , Oct 2022
Ligs: Learnable intrinsic-reward generation selection for multi-agent learningarXiv preprint arXiv:2112.02618, Oct 2021