# Meaningful human control: actionable properties for AI system development arXiv: https://arxiv.org/abs/2112.01298 ยท HTML: https://mlsanity.com/paper/2112.01298/ ## Key facts - Cited by 18 papers in the map (data through 14 Oct 2026). - Builds on 13 of its 108 references that are in the map. - First posted on arXiv 25 Nov 2021. ## Builds on (most cited first, 13 of 13) - [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019) - [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020) - [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020) - [Cooperative Inverse Reinforcement Learning](https://mlsanity.com/paper/1606.03137/) (2016) - [The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence](https://mlsanity.com/paper/2002.06177/) (2020) - [Artificial Intelligence: the global landscape of ethics guidelines](https://mlsanity.com/paper/1906.11668/) (2019) - [Discrimination in Online Ad Delivery](https://mlsanity.com/paper/1301.6822/) (2013) - [Occam's razor is insufficient to infer the preferences of irrational agents](https://mlsanity.com/paper/1712.05812/) (2017) - [Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases](https://mlsanity.com/paper/2102.11965/) (2021) - [Governance by Glass-Box: Implementing Transparent Moral Bounds for AI Behaviour](https://mlsanity.com/paper/1905.04994/) (2019) - [Reinforcement Learning and Inverse Reinforcement Learning with System 1 and System 2](https://mlsanity.com/paper/1811.08549/) (2018) - [Algorithms are not neutral: Bias in collaborative filtering](https://mlsanity.com/paper/2105.01031/) (2021) - [The Responsibility Quantification (ResQu) Model of Human Interaction with Automation](https://mlsanity.com/paper/1810.12644/) (2018) ## Built on by (most cited first, 18 of 18) - [Human-Centred Learning Analytics and AI in Education: a Systematic Literature Review](https://mlsanity.com/paper/2312.12751/) (2023) - [From Conversation to Orchestration: HCI Challenges and Opportunities in Interactive Multi-Agentic Systems](https://mlsanity.com/paper/2506.20091/) (2025) - [Unpacking Human-AI interactions: From interaction primitives to a design space](https://mlsanity.com/paper/2401.05115/) (2024) - [Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents](https://mlsanity.com/paper/2606.05391/) (2026) - [Grasping AI: experiential exercises for designers](https://mlsanity.com/paper/2310.01282/) (2023) - [Trustworthy AI: Deciding What to Decide](https://mlsanity.com/paper/2311.12604/) (2023) - [Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model](https://mlsanity.com/paper/2608.13867/) (2026) - [Developing and Evaluating a Design Method for Positive Artificial Intelligence](https://mlsanity.com/paper/2402.01499/) (2024) - [ARMCHAIR: integrated inverse reinforcement learning and model predictive control for human-robot collaboration](https://mlsanity.com/paper/2402.19128/) (2024) - [Human Tool: An MCP-Style Framework for Human-Agent Collaboration](https://mlsanity.com/paper/2602.12953/) (2026) - [Explaining Learned Reward Functions with Counterfactual Trajectories](https://mlsanity.com/paper/2402.04856/) (2024) - [The Unbearable Lightness of Prompting: A Critical Reflection on the Environmental Impact of genAI use in Design Education](https://mlsanity.com/paper/2501.16061/) (2025) - [Survey of Trustworthy AI: A Meta Decision of AI](https://mlsanity.com/paper/2306.00380/) (2023) - [Reflective Hybrid Intelligence for Meaningful Human Control in Decision-Support Systems](https://mlsanity.com/paper/2307.06159/) (2023) - [Human-Machine Teaming for UAVs: An Experimentation Platform](https://mlsanity.com/paper/2312.11718/) (2023) - [When Discourse Stalls: Moving Past Five Semantic Stopsigns about Generative AI in Design Research](https://mlsanity.com/paper/2503.08565/) (2025) - [When Life Gives You AI, Will You Turn It Into A Market for Lemons? Understanding How Information Asymmetries About AI System Capabilities Affect Market Outcomes and Adoption](https://mlsanity.com/paper/2601.21650/) (2026) - [From Protocols to Evidence: Bounded Claims for AI in Service of the Common Good](https://mlsanity.com/paper/2609.11910/) (2026) ## Abstract (arXiv) How can humans remain in control of artificial intelligence (AI)-based systems designed to perform tasks autonomously? Such systems are increasingly ubiquitous, creating benefits - but also undesirable situations where moral responsibility for their actions cannot be properly attributed to any particular person or group. The concept of meaningful human control has been proposed to address responsibility gaps and mitigate them by establishing conditions that enable a proper attribution of responsibility for humans; however, clear requirements for researchers, designers, and engineers are yet inexistent, making the development of AI-based systems that remain under meaningful human control challenging. In this paper, we address the gap between philosophical theory and engineering practice by identifying, through an iterative process of abductive thinking, four actionable properties for AI-based systems under meaningful human control, which we discuss making use of two applications scenarios: automated vehicles and AI-based hiring. First, a system in which humans and AI algorithms interact should have an explicitly defined domain of morally loaded situations within which the system ought to operate. Second, humans and AI agents within the system should have appropriate and mutually compatible representations. Third, responsibility attributed to a human should be commensurate with that human's ability and authority to control the system. Fourth, there should be explicit links between the actions of the AI agents and actions of humans who are aware of their moral responsibility. We argue that these four properties will support practically-minded professionals to take concrete steps toward designing and engineering for AI systems that facilitate meaningful human control.