# Characterizing AI Agents for Alignment and Governance

arXiv: https://arxiv.org/abs/2504.21848 · HTML: https://mlsanity.com/paper/2504.21848/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 64 references that are in the map.
- First posted on arXiv 30 Apr 2025.

## Builds on (most cited first, 17 of 17)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [Measuring Progress on Scalable Oversight for Large Language Models](https://mlsanity.com/paper/2211.03540/) (2022)
- [The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey](https://mlsanity.com/paper/2404.11584/) (2024)
- [Measuring AI Ability to Complete Long Software Tasks](https://mlsanity.com/paper/2503.14499/) (2025)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [Visibility into AI Agents](https://mlsanity.com/paper/2401.13138/) (2024)
- [Empowerment -- an Introduction](https://mlsanity.com/paper/1310.1863/) (2013)
- [Why human-AI relationships need socioaffective alignment](https://mlsanity.com/paper/2502.02528/) (2025)
- [Fully Autonomous AI Agents Should Not be Developed](https://mlsanity.com/paper/2502.02649/) (2025)
- [Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero](https://mlsanity.com/paper/2310.16410/) (2023)
- [Avoiding Side Effects By Considering Future Tasks](https://mlsanity.com/paper/2010.07877/) (2020)
- [Two Types of AI Existential Risk: Decisive and Accumulative](https://mlsanity.com/paper/2401.07836/) (2024)
- [The AI Agent Index](https://mlsanity.com/paper/2502.01635/) (2025)

## Built on by (most cited first, 30 of 30)

- [Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions](https://mlsanity.com/paper/2510.25445/) (2025)
- [Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI](https://mlsanity.com/paper/2505.19443/) (2025)
- [The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems](https://mlsanity.com/paper/2602.17753/) (2026)
- [Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution](https://mlsanity.com/paper/2506.01055/) (2025)
- [The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process](https://mlsanity.com/paper/2506.01080/) (2025)
- [Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs](https://mlsanity.com/paper/2601.11369/) (2026)
- [Intelligent AI Delegation](https://mlsanity.com/paper/2602.11865/) (2026)
- [Plasticity as the Mirror of Empowerment](https://mlsanity.com/paper/2505.10361/) (2025)
- [Distributional AGI Safety](https://mlsanity.com/paper/2512.16856/) (2025)
- [AI Agents and the Law](https://mlsanity.com/paper/2508.08544/) (2025)
- [How are AI agents used? Evidence from 177,000 MCP tools](https://mlsanity.com/paper/2603.23802/) (2026)
- [The Term 'Agent' Has Been Diluted Beyond Utility and Requires Redefinition](https://mlsanity.com/paper/2508.05338/) (2025)
- [Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value](https://mlsanity.com/paper/2512.03399/) (2025)
- [Incident Analysis for AI Agents](https://mlsanity.com/paper/2508.14231/) (2025)
- [Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment](https://mlsanity.com/paper/2601.10520/) (2026)
- [Agentic Inequality](https://mlsanity.com/paper/2510.16853/) (2025)
- [Agent Benchmarks Fail Public Sector Requirements](https://mlsanity.com/paper/2601.20617/) (2026)
- [AI as Entertainment](https://mlsanity.com/paper/2601.08768/) (2026)
- [Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents](https://mlsanity.com/paper/2510.04465/) (2025)
- [Draining the Energy Commons: Self-Defeating Over-Appropriation as a Coordination Failure in Agentic LLM Collectives](https://mlsanity.com/paper/2607.22188/) (2026)
- [Agentic AI Governance and Lifecycle Management in Healthcare](https://mlsanity.com/paper/2601.15630/) (2026)
- [Human Attribution of Causality to AI Across Agency, Misuse, and Misalignment](https://mlsanity.com/paper/2603.13236/) (2026)
- [Intelligence Impact Quotient (IIQ): A Framework for Measuring Organizational AI Impact](https://mlsanity.com/paper/2605.14455/) (2026)
- [Agentic Literacy Debt: A Structural Problem the AI Literacy Field Has Not Yet Named](https://mlsanity.com/paper/2605.27396/) (2026)
- [The DeepSpeak-Agentic Dataset](https://mlsanity.com/paper/2606.03686/) (2026)
- [The Perils of Agency: How Developers Perceive, Prioritize, and Address Risks in Agentic AI Products](https://mlsanity.com/paper/2606.15485/) (2026)
- [A Technical Typology of AI Systems in Public Administration](https://mlsanity.com/paper/2606.31755/) (2026)
- [Agentic AI Autonomy Assessment: A Decision-Support Framework Towards Governed Supply Chain Systems](https://mlsanity.com/paper/2607.25405/) (2026)
- [Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best](https://mlsanity.com/paper/2609.07627/) (2026)
- [Anticipatory Human Oversight of Agentic AI: A Philosophical Account](https://mlsanity.com/paper/2609.24242/) (2026)

## Abstract (arXiv)

The creation of effective governance mechanisms for AI agents requires a deeper understanding of their core properties and how these properties relate to questions surrounding the deployment and operation of agents in the world. This paper provides a characterization of AI agents that focuses on four dimensions: autonomy, efficacy, goal complexity, and generality. We propose different gradations for each dimension, and argue that each dimension raises unique questions about the design, operation, and governance of these systems. Moreover, we draw upon this framework to construct "agentic profiles" for different kinds of AI agents. These profiles help to illuminate cross-cutting technical and non-technical governance challenges posed by different classes of AI agents, ranging from narrow task-specific assistants to highly autonomous general-purpose systems. By mapping out key axes of variation and continuity, this framework provides developers, policymakers, and members of the public with the opportunity to develop governance approaches that better align with collective societal goals.