mlsanityData to 14 Oct 2026

Toward Embodied AGI: A Review of Embodied AI and the Road Ahead

arXiv 2505.14235 ↗First posted 20 May 2025cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Artificial General Intelligence (AGI) is often envisioned as inherently embodied. With recent advances in robotics and foundational AI models, we stand at the threshold of a new era-one marked by increasingly generalized embodied AI systems. This paper contributes to the discourse by introducing a systematic taxonomy of Embodied AGI spanning five levels (L1-L5). We review existing research and challenges at the foundational stages (L1-L2) and outline the key components required to achieve higher-level capabilities (L3-L5). Building on these insights and existing technologies, we propose a conceptual framework for an L3+ robotic brain, offering both a technical outlook and a foundation for future exploration.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 27 of its 41 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

27 of 41 references.

References · 27

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  5. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  6. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
  7. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  8. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  9. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,761
  10. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 838
  11. 2024GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulationcited by 296
  12. 2024Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representationscited by 289
15 more
  1. 2023Knowledge Editing for Large Language Models: A Surveycited by 194
  2. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 179
  3. 2023Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planningcited by 161
  4. 2024ALOHA Unleashed: A Simple Recipe for Robot Dexteritycited by 134
  5. 2025GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Datacited by 123
  6. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 83
  7. 2025Humanoid Locomotion and Manipulation: Current Progress and Challenges in Control, Planning, and Learningcited by 61
  8. 2024SocialBench: Sociality Evaluation of Role-Playing Conversational Agentscited by 50
  9. 2024Scaling Speech-Text Pre-training with Synthetic Interleaved Datacited by 47
  10. 2024Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigationcited by 44
  11. 2024How Far Are We From AGI: Are LLMs All We Need?cited by 31
  12. 2024Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Modelscited by 26
  13. 2021Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Controlcited by 24
  14. 2025Neural Brain: A Neuroscience-inspired Framework for Embodied Agentscited by 10
  15. 2025If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2025FLM-Audio: Natural Monologues Improves Native Full-Duplex Chatbots via Dual Trainingcited by 11
  2. 2025STORM: Search-Guided Generative World Models for Robotic Manipulationcited by 7
  3. 2025RoboEgo System Card: An Omnimodal Model with Native Full Duplexitycited by 5
  4. 2025EgoMem: Lifelong Memory Agent for Full-duplex Omnimodal Modelscited by 5
  5. 2026Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recoverycited by 4
  6. 2025Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AIcited by 3
  7. 2026Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trendscited by 1
  8. 2026Meta-ethics and AI: exploring the novel meta-ethical questions in the era of AIcited by 0