# Towards Adaptive Categories: Dimensional Governance for Agentic AI

arXiv: https://arxiv.org/abs/2505.11579 · HTML: https://mlsanity.com/paper/2505.11579/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 59 references that are in the map.
- First posted on arXiv 16 May 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 14 of 14)

- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing](https://mlsanity.com/paper/2001.00973/) (2020)
- [Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift](https://mlsanity.com/paper/1810.11953/) (2018)
- [Trustworthy AI: From Principles to Practices](https://mlsanity.com/paper/2110.01167/) (2021)
- [Auditing large language models: a three-layered approach](https://mlsanity.com/paper/2302.08500/) (2023)
- [Reviewable Automated Decision-Making: A Framework for Accountable Algorithmic Systems](https://mlsanity.com/paper/2102.04201/) (2021)
- [Human-AI Interactions in Public Sector Decision-Making: "Automation Bias" and "Selective Adherence" to Algorithmic Advice](https://mlsanity.com/paper/2103.02381/) (2021)
- [Position: Foundation Agents as the Paradigm Shift for Decision Making](https://mlsanity.com/paper/2405.17009/) (2024)
- [Optimizing Credit Limit Adjustments Under Adversarial Goals Using Reinforcement Learning](https://mlsanity.com/paper/2306.15585/) (2023)
- [Human-AI Governance (HAIG): A Trust-Utility Approach](https://mlsanity.com/paper/2505.01651/) (2025)
- [The Algorithmic State Architecture (ASA): An Integrated Framework for AI-Enabled Government](https://mlsanity.com/paper/2503.08725/) (2025)
- [Regulating Multifunctionality](https://mlsanity.com/paper/2502.15715/) (2025)

## Built on by (most cited first, 3 of 3)

- [With Great Capabilities Come Great Responsibilities: Introducing the Agentic Risk & Capability Framework for Governing Agentic AI Systems](https://mlsanity.com/paper/2512.22211/) (2025)
- [Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks](https://mlsanity.com/paper/2508.06411/) (2025)
- [Governing Well in the Algorithmic Age: The Foundations of Digital Statecraft](https://mlsanity.com/paper/2607.18483/) (2026)

## Abstract (arXiv)

As AI systems evolve from static tools to dynamic agents, traditional categorical governance frameworks -- based on fixed risk tiers, levels of autonomy, or human oversight models -- are increasingly insufficient on their own. Systems built on foundation models, self-supervised learning, and multi-agent architectures increasingly blur the boundaries that categories were designed to police. In this article, we make the case for dimensional governance: a framework that tracks how decision authority, process autonomy, and accountability (the 3As) distribute dynamically across human-AI relationships. A critical advantage of this approach is its ability to explicitly monitor system movement toward and across key governance thresholds, enabling pre-emptive adjustments before risks materialise. This dimensional approach provides the necessary foundation for more adaptive categorisation, enabling thresholds and classifications that can evolve with emerging capabilities. While categories remain essential for decision-making, building them upon dimensional foundations allows for context-specific adaptability and stakeholder-responsive governance that static approaches cannot achieve. We outline key dimensions, critical trust thresholds, and practical examples illustrating where rigid categorical frameworks fail -- and where a dimensional mindset could offer a more resilient and future-proof path forward for both governance and innovation at the frontier of artificial intelligence.