mlsanityData to 7 Oct 2026

Agentic AI Needs a Systems Theory

arXiv 2503.00237 ↗First posted 28 Feb 2025cs.AIcited by 19

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

The endowment of AI with reasoning capabilities and some degree of agency is widely viewed as a path toward more capable and generalizable systems. Our position is that the current development of agentic AI requires a more holistic, systems-theoretic perspective in order to fully understand their capabilities and mitigate any emergent risks. The primary motivation for our position is that AI development is currently overly focused on individual model capabilities, often ignoring broader emergent behavior, leading to a significant underestimation in the true capabilities and associated risks of agentic AI. We describe some fundamental mechanisms by which advanced capabilities can emerge from (comparably simpler) agents simply due to their interaction with the environment and other agents. Informed by an extensive amount of existing literature from various fields, we outline mechanisms for enhanced agent cognition, emergent causal reasoning ability, and metacognitive awareness. We conclude by presenting some key open challenges and guidance for the development of agentic AI. We emphasize that a systems-level perspective is essential for better understanding, and purposefully shaping, agentic AI systems.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 39 of its 150 references that are in the map. First posted on arXiv 28 Feb 2025.

Builds on

39 of 150 references.

References · 39

  1. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  2. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  3. 2022A Generalist Agentcited by 802
  4. 2018Learning Dexterous In-Hand Manipulationcited by 643
  5. 2023Language Is Not All You Need: Aligning Perception with Language Modelscited by 543
  6. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 424
  7. 2024Automated Design of Agentic Systemscited by 360
  8. 2023An Embodied Generalist Agent in 3D Worldcited by 355
  9. 2024Alignment faking in large language modelscited by 316
  10. 2024TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Taskscited by 306
  11. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  12. 2024MM-LLMs: Recent Advances in MultiModal Large Language Modelscited by 277
27 more
  1. 2024Frontier Models are Capable of In-context Schemingcited by 252
  2. 2023Emu: Generative Pretraining in Multimodalitycited by 156
  3. 2023Causal Parrots: Large Language Models May Talk Causality But Are Not Causalcited by 146
  4. 2023Can Large Language Models Infer Causation from Correlation?cited by 142
  5. 2023Harms from Increasingly Agentic Algorithmic Systemscited by 134
  6. 2024A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directionscited by 115
  7. 2024Evaluating the World Model Implicit in a Generative Modelcited by 107
  8. 2024Robust agents learn causal world modelscited by 81
  9. 2023Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMscited by 64
  10. 2024CRISPR-GPT for Agentic Automation of Gene-editing Experimentscited by 56
  11. 2025Fully Autonomous AI Agents Should Not be Developedcited by 43
  12. 2024Uncertainty quantification in fine-tuned LLMs using LoRA ensemblescited by 35
  13. 2024SemGrasp: Semantic Grasp Generation via Language Aligned Discretizationcited by 29
  14. 2022Discovering Agentscited by 28
  15. 2023Human-AI Coevolutioncited by 27
  16. 2023CRAB: Assessing the Strength of Causal Relationships Between Real-world Eventscited by 27
  17. 2024Aviary: training language agents on challenging scientific taskscited by 23
  18. 2020AdaGrasp: Learning an Adaptive Gripper-Aware Grasping Policycited by 16
  19. 2024A Critical Review of Causal Reasoning Benchmarks for Large Language Modelscited by 13
  20. 2024Active Inference as a Model of Agencycited by 12
  21. 2024Imagining and building wise machines: The centrality of AI metacognitioncited by 12
  22. 2024Challenges in Human-Agent Communicationcited by 11
  23. 2024ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systemscited by 8
  24. 2024Transforming Agency. On the mode of existence of Large Language Modelscited by 7
  25. 2024Towards Measuring Goal-Directedness in AI Systemscited by 7
  26. 2025Lessons from complexity theory for AI governancecited by 5
  27. 2025Agency Is Frame-Dependentcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 13; 2026: 6.

19 papers.

Sort:

By area:

  1. 2025Small Language Models are the Future of Agentic AIcited by 254
  2. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 167
  3. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  4. 2025Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AIcited by 39
  5. 2025AgentGuard: Runtime Verification of AI Agentscited by 16
  6. 2025Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspectivecited by 12
  7. 2025Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AIcited by 6
  8. 2025GateLens: A Reasoning-Enhanced LLM Agent for Automotive Software Release Analyticscited by 4
  9. 2025Reliable agent engineering should integrate machine-compatible organizational principlescited by 2
  10. 2025The Effectiveness of Approximate Regularized Replay for Efficient Supervised Fine-Tuning of Large Language Modelscited by 2
  11. 2025Socio-technical aspects of Agentic AIcited by 2
  12. 2026Autonomy and Agency in Agentic AI: Architectural Tactics for Regulated Contextscited by 2
7 more
  1. 2026Design Methodology and Performance Trade-offs Management for Distributed and Compound AI Systemscited by 1
  2. 2026Tangent: An Empirical Study of Testing Practices for LLM-Based Agent Applicationscited by 1
  3. 2026Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market Decisionscited by 1
  4. 2025Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty?cited by 0
  5. 2025Situating AI Agents in their World: Aspective Agentic AI for Dynamic Partially Observable Information Systemscited by 0
  6. 2026Visioning Human-Agentic AI Teaming: Continuity, Tension, and Future Researchcited by 0
  7. 2026Autonoma: A Hierarchical Multi-Agent Framework for End-to-End Workflow Automationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Agentifying Agentic AI
  2. 2026Understanding Cognition-Induced Risks in Agentic AI Systems
  3. 2025Exploring Agentic Artificial Intelligence Systems: Towards a Typological Framework
  4. 2025Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience
  5. 2025A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond
  6. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey
  7. 2026Agentic Design Patterns: A System-Theoretic Framework
  8. 2026The Path Ahead for Agentic AI: Challenges and Opportunities