Self-evolving Embodied AI
Not on the map. Why?
Abstract (arXiv)
Embodied Artificial Intelligence (AI) is an intelligent system formed by agents and their environment through active perception, embodied cognition, and action interaction. Existing embodied AI remains confined to human-crafted setting, in which agents are trained on given memory and construct models for given tasks, enabling fixed embodiments to interact with relatively static environments. Such methods fail in in-the-wild setting characterized by variable embodiments and dynamic open environments. This paper introduces self-evolving embodied AI, a new paradigm in which agents operate based on their changing state and environment with memory self-updating, task self-switching, environment self-prediction, embodiment self-adaptation, and model self-evolution, aiming to achieve continually adaptive intelligence with autonomous evolution. Specifically, we present the definition, framework, components, and mechanisms of self-evolving embodied AI, systematically review state-of-the-art works for realized components, discuss practical applications, and point out future research directions. We believe that self-evolving embodied AI enables agents to autonomously learn and interact with environments in a human-like manner and provide a new perspective toward general artificial intelligence.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 82 of its 99 references that are in the map. First posted on arXiv 4 Feb 2026.
Builds on
82 of 99 references.
References · 82
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
- 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
- 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
- 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
- 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
- 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
- 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 982
- 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
- 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
- 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 738
38 more
- 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 722
- 2024Genie: Generative Interactive Environmentscited by 706
- 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 373
- 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
- 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 256
- 2025TTRL: Test-Time Reinforcement Learningcited by 253
- 2024WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learningcited by 243
- 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representationcited by 239
- 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learningcited by 220
- 2025R-Zero: Self-Evolving Reasoning LLM from Zero Datacited by 210
- 2024Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapterscited by 199
- 2025Learning to Reason without External Rewardscited by 199
- 2025A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systemscited by 177
- 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 175
- 2025Matrix-game 2.0: An open-source real-time and streaming interactive world modelcited by 174
- 2021BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environmentscited by 161
- 2024Understanding World or Predicting Future? A Comprehensive Survey of World Modelscited by 161
- 2017Preparing for the Unknown: Learning a Universal Policy with Online System Identificationcited by 129
- 2025Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Taskscited by 128
- 2025Training Agents Inside of Scalable World Modelscited by 122
- 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 119
- 2025Self-Evolving Curriculum for LLM Reasoningcited by 107
- 2023HomeRobot: Open-Vocabulary Mobile Manipulationcited by 104
- 2024Symbolic Learning Enables Self-Evolving Agentscited by 104
- 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 99
- 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agentscited by 99
- 2025MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraftcited by 93
- 2025MemInsight: Autonomous Memory Augmentation for LLM Agentscited by 84
- 2025AgentEvolver: Towards Efficient Self-Evolving Agent Systemcited by 77
- 2024Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluationcited by 73
- 2025SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experiencecited by 68
- 2025Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoningcited by 68
- 2025Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolutioncited by 65
- 2025EnerVerse: Envisioning Embodied Future Space for Robotics Manipulationcited by 59
- 2025Multi-Agent Evolve: LLM Self-Improve through Co-evolutioncited by 58
- 2025WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Modelcited by 56
- 2024A Survey on Robotics with Foundation Models: toward Embodied AIcited by 53
- 2024MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Controlcited by 52
50 most cited of 82 All 82 (JSON)
Built on by
Citing papers per year: 2026: 2.
2 papers.