mlsanityData to 14 Oct 2026

Position: Foundation Agents as the Paradigm Shift for Decision Making

arXiv 2405.17009 ↗First posted 27 May 2024cs.AIcited by 9

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Decision making demands intricate interplay between perception, memory, and reasoning to discern optimal policies. Conventional approaches to decision making face challenges related to low sample efficiency and poor generalization. In contrast, foundation models in language and vision have showcased rapid adaptation to diverse new tasks. Therefore, we advocate for the construction of foundation agents as a transformative shift in the learning paradigm of agents. This proposal is underpinned by the formulation of foundation agents with their fundamental characteristics and challenges motivated by the success of large language models (LLMs). Moreover, we specify the roadmap of foundation agents from large interactive data collection or generation, to self-supervised pretraining and adaptation, and knowledge and value alignment with LLMs. Lastly, we pinpoint critical research questions derived from the formulation and delineate trends for foundation agents supported by real-world use cases, addressing both technical and theoretical aspects to propel the field towards a more comprehensive and impactful future.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 93 of its 119 references that are in the map. First posted on arXiv 27 May 2024.

Builds on

93 of 119 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023A Survey on Large Language Model based Autonomous Agents22 Aug
  2. 2023AgentBench: Evaluating LLMs as Agents7 Aug
  3. 2023InterAct: Exploring the Potentials of ChatGPT as a Cooperative Agent3 Aug
  4. 2023Building Cooperative Embodied Agents Modularly with Large Language Models5 Jul
  5. 2022A Generalist Agent12 May

Other references · 88

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2023GPT-4 Technical Reportcited by 18,396
  6. 2022Training language models to follow instructions with human feedbackcited by 15,971
  7. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  8. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  9. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  10. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  11. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  12. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
38 more
  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  6. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  7. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  8. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  9. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  10. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  11. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  12. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  13. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  14. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  15. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  16. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  17. 2018DeepMind Control Suitecited by 956
  18. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
  19. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 862
  20. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  21. 2024Genie: Generative Interactive Environmentscited by 747
  22. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  23. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 644
  24. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  25. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 571
  26. 2023Learning Universal Policies via Text-Guided Video Generationcited by 522
  27. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  28. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 478
  29. 2023Learning Interactive Real-World Simulatorscited by 458
  30. 2022VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Trainingcited by 395
  31. 2017FeUdal Networks for Hierarchical Reinforcement Learningcited by 337
  32. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 327
  33. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 316
  34. 2022Behavior Transformers: Cloning k modes with one stonecited by 304
  35. 2023Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Actioncited by 302
  36. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 289
  37. 2020Decoupling Representation Learning from Reinforcement Learningcited by 269
  38. 2023RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulationcited by 218

50 most cited of 88 All 88 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 5; 2026: 1.

9 papers.

  1. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  2. 2024XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learningcited by 14
  3. 2025Distributive Fairness in Large Language Models: Evaluating Alignment with Human Valuescited by 9
  4. 2024Enhancing Language Model Rationality with Bi-Directional Deliberation Reasoningcited by 5
  5. 2024A Taxonomy of Architecture Options for Foundation Model-based Agents: Analysis and Decision Modelcited by 4
  6. 2025Human-AI Governance (HAIG): A Trust-Utility Approachcited by 4
  7. 2025Towards Adaptive Categories: Dimensional Governance for Agentic AIcited by 3
  8. 2025Optimization Problem Solving Can Transition to Evolutionary Agentic Workflowscited by 0
  9. 2026The Future of AI is Many, Not Onecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Foundation Model Sherpas: Guiding Foundation Models through Knowledge and Reasoning
  2. 2025Foundation Models as World Models: A Foundational Study in Text-Based GridWorlds
  3. 2023A Survey of Reasoning with Foundation Models
  4. 2023The Rise and Potential of Large Language Model Based Agents: A Survey
  5. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
  6. 2025Agent-as-Tool: A Study on the Hierarchical Decision Making with Reinforcement Learning
  7. 2025Scaling Agents via Continual Pre-training
  8. 2023ExpeL: LLM Agents Are Experiential Learners