Data to 14 Oct 2026

Characterizing AI Agents for Alignment and Governance

arXiv 2504.21848 ↗First posted 30 Apr 2025cs.CY cs.AI cs.SYcited by 30

Not on the map. Why?

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.

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

17 of 64 references.

References · 17

2023GPT-4 Technical Reportcited by 18,396
2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
2023Cognitive Architectures for Language Agentscited by 429
2024Mechanistic Interpretability for AI Safety -- A Reviewcited by 422
2024Understanding the planning of LLM agents: A surveycited by 421
2022Measuring Progress on Scalable Oversight for Large Language Modelscited by 225
2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Surveycited by 168
2025Measuring AI Ability to Complete Long Software Taskscited by 156
2023Harms from Increasingly Agentic Algorithmic Systemscited by 135
2024Visibility into AI Agentscited by 79
2013Empowerment -- an Introductioncited by 68
2025Why human-AI relationships need socioaffective alignmentcited by 47

5 more

2025Fully Autonomous AI Agents Should Not be Developedcited by 45
2023Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZerocited by 42
2020Avoiding Side Effects By Considering Future Taskscited by 32
2024Two Types of AI Existential Risk: Decisive and Accumulativecited by 22
2025The AI Agent Indexcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 12; 2026: 18.

30 papers.

Sort:

By area:

2025Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directionscited by 48
2025Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AIcited by 42
2026The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systemscited by 30
2025Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Executioncited by 26
2025The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Processcited by 21
2026Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphscited by 20
2026Intelligent AI Delegationcited by 18
2025Plasticity as the Mirror of Empowermentcited by 12
2025Distributional AGI Safetycited by 12
2025AI Agents and the Lawcited by 9
2026How are AI agents used? Evidence from 177,000 MCP toolscited by 7
2025The Term 'Agent' Has Been Diluted Beyond Utility and Requires Redefinitioncited by 6

18 more

2025Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Valuecited by 6
2025Incident Analysis for AI Agentscited by 5
2026Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignmentcited by 5
2025Agentic Inequalitycited by 3
2026Agent Benchmarks Fail Public Sector Requirementscited by 3
2026AI as Entertainmentcited by 2
2025Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agentscited by 1
2026Draining the Energy Commons: Self-Defeating Over-Appropriation as a Coordination Failure in Agentic LLM Collectivescited by 1
2026Agentic AI Governance and Lifecycle Management in Healthcarecited by 0
2026Human Attribution of Causality to AI Across Agency, Misuse, and Misalignmentcited by 0
2026Intelligence Impact Quotient (IIQ): A Framework for Measuring Organizational AI Impactcited by 0
2026Agentic Literacy Debt: A Structural Problem the AI Literacy Field Has Not Yet Namedcited by 0
2026The DeepSpeak-Agentic Datasetcited by 0
2026The Perils of Agency: How Developers Perceive, Prioritize, and Address Risks in Agentic AI Productscited by 0
2026A Technical Typology of AI Systems in Public Administrationcited by 0
2026Agentic AI Autonomy Assessment: A Decision-Support Framework Towards Governed Supply Chain Systemscited by 0
2026Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Bestcited by 0
2026Anticipatory Human Oversight of Agentic AI: A Philosophical Accountcited by 0

Similar, not cited

Close in wording, no citation either way