# Agentic AI Needs a Systems Theory

arXiv: https://arxiv.org/abs/2503.00237 · HTML: https://mlsanity.com/paper/2503.00237/

## Key facts

- Cited by 19 papers in the map (data through 14 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.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 39)

- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [Language Is Not All You Need: Aligning Perception with Language Models](https://mlsanity.com/paper/2302.14045/) (2023)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [An Embodied Generalist Agent in 3D World](https://mlsanity.com/paper/2311.12871/) (2023)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks](https://mlsanity.com/paper/2412.14161/) (2024)
- [Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models](https://mlsanity.com/paper/2305.19187/) (2023)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [MM-LLMs: Recent Advances in MultiModal Large Language Models](https://mlsanity.com/paper/2401.13601/) (2024)
- [Emu: Generative Pretraining in Multimodality](https://mlsanity.com/paper/2307.05222/) (2023)
- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (2023)
- [Can Large Language Models Infer Causation from Correlation?](https://mlsanity.com/paper/2306.05836/) (2023)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions](https://mlsanity.com/paper/2412.05563/) (2024)
- [Evaluating the World Model Implicit in a Generative Model](https://mlsanity.com/paper/2406.03689/) (2024)
- [Robust agents learn causal world models](https://mlsanity.com/paper/2402.10877/) (2024)
- [Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs](https://mlsanity.com/paper/2310.07251/) (2023)
- [CRISPR-GPT for Agentic Automation of Gene-editing Experiments](https://mlsanity.com/paper/2404.18021/) (2024)
- [Fully Autonomous AI Agents Should Not be Developed](https://mlsanity.com/paper/2502.02649/) (2025)
- [Uncertainty quantification in fine-tuned LLMs using LoRA ensembles](https://mlsanity.com/paper/2402.12264/) (2024)
- [SemGrasp: Semantic Grasp Generation via Language Aligned Discretization](https://mlsanity.com/paper/2404.03590/) (2024)
- [Discovering Agents](https://mlsanity.com/paper/2208.08345/) (2022)
- [CRAB: Assessing the Strength of Causal Relationships Between Real-world Events](https://mlsanity.com/paper/2311.04284/) (2023)
- [Human-AI Coevolution](https://mlsanity.com/paper/2306.13723/) (2023)
- [Aviary: training language agents on challenging scientific tasks](https://mlsanity.com/paper/2412.21154/) (2024)
- [AdaGrasp: Learning an Adaptive Gripper-Aware Grasping Policy](https://mlsanity.com/paper/2011.14206/) (2020)

## Built on by (most cited first, 19 of 19)

- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges](https://mlsanity.com/paper/2505.10468/) (2025)
- [A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures](https://mlsanity.com/paper/2506.19676/) (2025)
- [Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI](https://mlsanity.com/paper/2505.19443/) (2025)
- [AgentGuard: Runtime Verification of AI Agents](https://mlsanity.com/paper/2509.23864/) (2025)
- [Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective](https://mlsanity.com/paper/2504.03255/) (2025)
- [Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AI](https://mlsanity.com/paper/2509.20175/) (2025)
- [GateLens: A Reasoning-Enhanced LLM Agent for Automotive Software Release Analytics](https://mlsanity.com/paper/2503.21735/) (2025)
- [Autonomy and Agency in Agentic AI: Architectural Tactics for Regulated Contexts](https://mlsanity.com/paper/2605.12105/) (2026)
- [Reliable agent engineering should integrate machine-compatible organizational principles](https://mlsanity.com/paper/2512.07665/) (2025)
- [The Effectiveness of Approximate Regularized Replay for Efficient Supervised Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2512.22337/) (2025)
- [Socio-technical aspects of Agentic AI](https://mlsanity.com/paper/2601.06064/) (2025)
- [Tangent: An Empirical Study of Testing Practices for LLM-Based Agent Applications](https://mlsanity.com/paper/2608.08413/) (2026)
- [Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty?](https://mlsanity.com/paper/2508.01109/) (2025)
- [Design Methodology and Performance Trade-offs Management for Distributed and Compound AI Systems](https://mlsanity.com/paper/2606.14350/) (2026)
- [Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market Decisions](https://mlsanity.com/paper/2608.18078/) (2026)
- [Situating AI Agents in their World: Aspective Agentic AI for Dynamic Partially Observable Information Systems](https://mlsanity.com/paper/2509.03380/) (2025)
- [Visioning Human-Agentic AI Teaming: Continuity, Tension, and Future Research](https://mlsanity.com/paper/2603.04746/) (2026)
- [Autonoma: A Hierarchical Multi-Agent Framework for End-to-End Workflow Automation](https://mlsanity.com/paper/2603.19270/) (2026)

## 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.