Humans Coexist, So Must Embodied Artificial Agents
Not on the map. Why?
Abstract (arXiv)
This paper introduces the concept of coexistence for embodied artificial agents and argues that it is a prerequisite for long-term, in-the-wild interaction with humans. Contemporary embodied artificial agents excel in static, predefined tasks but fall short in dynamic and long-term interactions with humans. On the other hand, humans can adapt and evolve continuously, exploiting the situated knowledge embedded in their environment and other agents, thus contributing to meaningful interactions. We take an interdisciplinary approach at different levels of organization, drawing from biology and design theory, to understand how human and non-human organisms foster entities that coexist within their specific environments. Finally, we propose key research directions for the artificial intelligence community to develop coexisting embodied agents, focusing on the principles, hardware and learning methods responsible for shaping them.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 54 of its 157 references that are in the map. First posted on arXiv 7 Feb 2025.
Builds on
54 of 157 references.
References · 54
- 2017Attention Is All You Needcited by 59,932
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2023GPT-4 Technical Reportcited by 18,132
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
- 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
- 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
- 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
- 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
38 more
- 2020Meta-Learning in Neural Networks: A Surveycited by 944
- 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
- 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
- 2024Genie: Generative Interactive Environmentscited by 706
- 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
- 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 573
- 2021LiT: Zero-Shot Transfer with Locked-image text Tuningcited by 572
- 2015Illuminating search spaces by mapping elitescited by 406
- 2024Diffusion for World Modeling: Visual Details Matter in Ataricited by 285
- 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
- 2023Foundation Models in Robotics: Applications, Challenges, and the Futurecited by 212
- 2023Cultural Bias and Cultural Alignment of Large Language Modelscited by 149
- 2022DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulationcited by 129
- 2023Language Models Meet World Models: Embodied Experiences Enhance Language Modelscited by 123
- 2023VDT: General-purpose Video Diffusion Transformers via Mask Modelingcited by 102
- 2023A Definition of Continual Reinforcement Learningcited by 98
- 2023Large Language Models as Generalizable Policies for Embodied Taskscited by 86
- 2024Open-Endedness is Essential for Artificial Superhuman Intelligencecited by 79
- 2024No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performancecited by 75
- 2021Understanding Domain Randomization for Sim-to-real Transfercited by 69
- 2020Counterfactual Credit Assignment in Model-Free Reinforcement Learningcited by 60
- 2023A Survey of Temporal Credit Assignment in Deep Reinforcement Learningcited by 56
- 2023How Novices Use LLM-Based Code Generators to Solve CS1 Coding Tasks in a Self-Paced Learning Environmentcited by 55
- 2024PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigatorscited by 55
- 2023Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learningcited by 49
- 2017Human-in-the-loop Artificial Intelligencecited by 40
- 2023Learnability and Algorithm for Continual Learningcited by 28
- 2024Is ChatGPT Transforming Academics' Writing Style?cited by 26
- 2024LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actionscited by 21
- 2024Automating the Search for Artificial Life with Foundation Modelscited by 20
- 2020Jelly Bean World: A Testbed for Never-Ending Learningcited by 19
- 2024Measuring Social Norms of Large Language Modelscited by 16
- 2024Position: Benchmarking is Limited in Reinforcement Learning Researchcited by 15
- 2020Modeling and Predicting Trust Dynamics in Human-Robot Teaming: A Bayesian Inference Approachcited by 14
- 2022Survey on Evolutionary Deep Learning: Principles, Algorithms, Applications and Open Issuescited by 12
- 2024A Super-human Vision-based Reinforcement Learning Agent for Autonomous Racing in Gran Turismocited by 12
- 2025Evolution and The Knightian Blindspot of Machine Learningcited by 11
- 2019Automated shapeshifting for function recovery in damaged robotscited by 8
50 most cited of 54 All 54 (JSON)
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.