Human Oversight of AI

Follow this topic Ask about this topic

Momentum

13 papers in the last four weeks, up 117% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 121

May 8, 2026cs.SE

From Assistance to Agency: Rethinking Autonomy and Control in CI/CD Pipelines

AI agents are assuming active roles in Continuous Integration and Continuous Deployment (CI/CD) workflows, yet the research community lacks a shared vocabulary for describing what it means for CI/CD to be agentic, how much decision authority is delegated, and where control should reside. This paper presents a vision of agentic CI/CD in which the central challenge is not improving task performance but designing authority transfer, defined as the delegation of operational decisions from human-controlled pipelines to agent systems under specified constraints and recourse mechanisms. To structure this argument, we introduce a distinction between data-plane authority (localized interventions such as patch generation and test reruns) and control-plane authority (modifications to pipeline configuration, deployment policies, and approval gates). Drawing on research prototypes and industrial platforms, we show that current systems operate mainly at the data plane under bounded autonomy, with safety achieved through surrounding governance infrastructure rather than intrinsic agent guarantees. We identify three recurring patterns: constrained autonomy as the dominant design, external governance as the primary safety mechanism, and a widening gap between deployment momentum and evaluation methodology. We propose a research agenda in which control-plane safety and governance mechanisms represent the most urgent open problem, followed by formalization of autonomy boundaries, evaluation frameworks, and human--agent coordination.

Marcus Emmanuel Barnes, Taher A. Ghaleb, Safwat Hassan

Faculty of Information University of Toronto Toronto, Ontario, Canada · Department of Computer Science Trent University Peterborough, Ontario, Canada

Software Engineering Agents Agentic Workflows AI Agent Governance Human Oversight of AI

May 7, 2026cs.AI

Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight

Reasoning in Large Language Models (LLMs) poses a challenge for oversight as many misaligned behaviors do not surface until reasoning concludes. To address this, we introduce Behavior Cue Reasoning for making LLM reasoning more controllable and monitorable. Behavior Cues are special token sequences that a model is trained to emit immediately before specific implicit and explicit behaviors, acting as dual purpose signal and control levers. When fine-tuning a weaker external monitor with Reinforcement Learning for reasoning oversight, a compressed view of only information surfaced by Behavior Cues is sufficient signal for the monitor to prune up to 50% of otherwise wasted reasoning tokens in complex math problem solving. When leveraged by an almost optimal rule-based monitor in an environment where excessive constraint violations results in failure, Behavior Cues allows for the recovery of safe actions from 80% of reasoning traces that would otherwise end with the proposal of an unsafe action, more than doubling the success rate from 46% to 96%. Through evaluation across two model families and three domains, we show that Behavior Cue Reasoning improves reasoning monitorability and controllability with no cost to performance. More broadly, our work progresses scalable oversight by demonstrating how the monitored model itself can be trained to reason more tractably to oversight. Code: https://github.com/christopherzc/behavior-cues

Christopher Z. Cui, Taylor W. Killian, Prithviraj Ammanabrolu

University of California, San Diego · 2Brigham Young University

Scalable Oversight LLM Safety Human Oversight of AI CoT Monitoring

May 7, 2026cs.CY

From Review to Design: Ethical Multimodal Driver Monitoring Systems for Risk Mitigation, Incident Response, and Accountability in Automated Vehicles

As vehicles transition toward higher levels of automation, Driver Monitoring Systems (DMS) have become essential for ensuring human oversight, safety, and regulatory compliance in a vehicle. These systems rely on multimodal sensing and AI-driven inference to assess driver attention, cognitive state, and readiness to take control. While technologically promising, their deployment introduces a complex set of ethical and legal challenges - ranging from privacy and consent to data ownership and algorithmic fairness. While overarching frameworks such as the GDPR, EU AI Act, and IEEE standards offer important guidance, they lack the specificity required for addressing the unique risks posed by in-cabin sensing technologies. This paper adopts a review-to-design perspective, critically examining existing regulatory instruments and ethical frameworks -- such as the GDPR, the EU AI Act, and IEEE guidelines -- and identifying gaps in their applicability to the distinctive risks posed by multimodal, AI-enabled in-cabin monitoring. Building on this review, we propose a modular ethical design framework tailored specifically to Driver Monitoring Systems. The framework translates high-level principles into actionable design and deployment guidance, including user-configurable consent mechanisms, fairness-aware model development, transparency and explainability tools, and safeguards for driver emotional well-being. Finally, the paper outlines a risk analysis and failure mitigation strategy, emphasizing proactive incident response and accountability mechanisms tailored to the DMS context. Together, these contributions aim to inform the development of transparent, trustworthy, and human-centered driver monitoring systems for next-generation autonomous vehicles.

Bilal Khana, Waseem Shariff, Rory Coyne +2

C3I Imaging Lab, School of Engineering, University of Galway · Royal College of Surgeons in Ireland

AI Accountability Autonomous Driving Human Oversight of AI Driver Monitoring Responsible AI

May 7, 2026cs.AI

Automated alignment is harder than you think

A leading proposal for aligning artificial superintelligence (ASI) is to use AI agents to automate an increasing fraction of alignment research as capabilities improve. We argue that, even when research agents are not scheming to deliberately sabotage alignment work, this plan could produce compelling but catastrophically misleading safety assessments resulting in the unintentional deployment of misaligned AI. This could happen because alignment research involves many hard-to-supervise fuzzy tasks (tasks without clear evaluation criteria, for which human judgement is systematically flawed). Consequently, research outputs will contain systematic, undetected errors, and even correct outputs could be incorrectly aggregated into overconfident safety assessments. This problem is likely to be worse for automated alignment research than for human-generated alignment research for several reasons: 1) optimisation pressure means agent-generated mistakes are concentrated among those that human reviewers are least likely to catch; 2) agents are likely to produce errors that do not resemble human mistakes; 3) AI-generated alignment solutions may involve arguments humans cannot evaluate; and 4) shared weights, data and training processes may make AI outputs more correlated than human equivalents. Therefore, agents must be trained to reliably perform hard-to-supervise fuzzy tasks. Generalisation and scalable oversight are the leading candidates for achieving this but both face novel challenges in the context of automated alignment.

Aleksandr Bowkis, Marie Davidsen Buhl, Jacob Pfau +1

AI Security Institute

Scalable Oversight AI Alignment AI Safety Evaluation Human Oversight of AI Autonomous Research Agents

May 6, 2026cs.HC

Making AI Drafts Count: A Quality Threshold in Audio Description Workflows

Audio description (AD) narrates visual elements in video for blind and low-vision audiences. Recent work has shown that giving novice describers an AI-generated draft to start from helps produce higher-quality AD and lowers the barrier to entry. What remains an open question is how draft quality shapes the editing process. We investigate this through GenAD, an AD generation pipeline that incorporates accessibility guidelines and contextual video information, and RefineAD, an editing interface for human revisions. Human-AI contributions are measured across text, timing, and delivery. In a within-subjects study, we compared authoring from scratch against editing AI drafts of varying quality. GenAD drafts cut completion time by more than half and significantly reduced cognitive load. In contrast, baseline drafts generated from simple, unguided prompts offered only modest benefits, pointing to a minimum quality threshold for effectiveness. Qualitative findings suggest this threshold is content-dependent; as visual complexity increases, so does the quality needed from AI drafts. We propose this as a design principle: effective AI assistance should clear a quality threshold suited to the target content, rather than simply be present.

Lana Do, Shasta Ihorn, Charity M. Pitcher-Cooper +7

Northeastern University United States · San Francisco State University United States · The Smith-Kettlewell Eye Research Institute United States +1

Human Oversight of AI Human-AI Collaboration

May 5, 2026cs.DC

A Workflow-Oriented Framework for Asynchronous Human-AI Collaboration in Hybrid and Compute-Intensive HPC Environments

Human involvement is critical in training and deploying AI systems in high-stakes defence and security contexts. However, real-time interaction is impractical in HPC environments due to compute intensity and resource constraints. We present a workflow framework that enables asynchronous human-AI collaboration across hybrid infrastructures, including HPC clusters, local machines, and cloud platforms. Workflows can pause at defined checkpoints for human input without halting underlying compute jobs, preventing idle resources and enabling non-blocking supervision. The framework supports interaction with SLURM-based scheduling, containerized and native tasks, and is customized for scenarios requiring human judgment and adaptability. We demonstrate its application in model training on systems like MareNostrum 5, highlighting benefits in portability, efficiency, and oversight in operational AI workflows.

Sergio Mendoza, Cedric Bhihe, Natalia Zamora +5

1Barcelona Supercomputing Center, Spain · 2NTT DATA, Spain

High-Performance Computing Human-in-the-Loop AI Human Oversight of AI Human-AI Collaboration

May 4, 2026cs.AI

From Tool to Agent: How Worker Needs Reorganize Across the Agentic Roles of Workplace AI

As AI systems gain agency in workplaces, workers increasingly interact with systems that do more than support tasks: they make decisions, allocate work, and shape how workers communicate with others. We interviewed 16 workers in healthcare, finance, and management about their daily interactions with workplace AI systems. Across these domains, AI occupied three agentic roles: \emph{assistant}, supporting worker decision-making; \emph{arbiter}, making consequential decisions that workers had to explain to downstream stakeholders; and \emph{manager}, directing work and displacing social structures through which work had been negotiated and learned. We find that worker needs depended on how decision authority and accountability were configured around the AI system. Explanation, control, accountability, and communication each took different meanings depending on whether AI supported, decided, or directed work. We contribute a role-based account of workplace human-agent interaction and identify accountability-authority asymmetry as a mechanism through which AI deployments can place responsibility on workers for outcomes whose authority has shifted to AI. We discuss implications for designing workplace AI around both the agent and its surrounding agency configuration.

Christine P. Lee, Min Kyung Lee, Bilge Mutlu

University of Wisconsin–Madison, Madison, WI, USA · University of Texas at Austin, Austin, TX, USA

Human-AI Interaction Human-AI Decision Making Human Oversight of AI AI and Labor

May 2, 2026cs.HC

Less Interaction But More Explanation: A Communication Perspective on Agentic AI Interfaces

AI systems have long been expected to interact with users, answering questions, generating content, and continuing (social) conversations. Agentic AI, however, breaks from this expectation, as its primary objective is workflow execution on behalf of the users. If a system becomes more agentic, do users need less interaction with the system? Our answer is: less routine back-and-forth, but more communication for oversight and explanation, as agentic AI proactively acts, not just responds. Grounded in a communication perspective, we discuss how users perceive the communicative roles of AI systems (whether as the source of actions or merely a channel), and how this can shape trust. Because agentic AI can play multiple communicative roles, it can complicate this source perception and introduce potential risks. To address this, we propose three types of explanations that agentic AI needs to incorporate (action-process, uncertainty, and coordination), and suggest that customization affordances that allow users to decide when and which explanations they see may be key to preserving human agency as AI autonomy increases.

Eunchae Jang, S. Shyam Sundar

Media Effects Research Laboratory, Pennsylvania State University, Pennsylvania, USA · Center for Socially Responsible AI, Pennsylvania State University, Pennsylvania, USA

Explainable Artificial Intelligence Human-AI Interaction Trust in AI Human Oversight of AI Agentic AI

May 2, 2026cs.AI

AI Safety as Control of Irreversibility: A Systems Framework for Decision-Energy and Sovereignty Boundaries

Recent AI systems compress the distance between capability growth and capability deployment. Earlier high-risk technologies were slowed by capital intensity, physical bottlenecks, organizational inertia, and specialized supply chains. By contrast, AI capabilities can be copied, invoked, embedded in workflows, and scaled across institutions at low marginal cost. This paper argues that declining deployment friction changes the safety problem at its root. Safety is not only local output correctness or preference alignment, but the control of irreversibility under rising decision density. The paper formalizes this claim through decision-energy density: the rate-weighted capacity of a node to generate, evaluate, select, and execute consequential decisions. It then identifies three sovereignty boundaries that determine whether AI remains an amplifier within a human-governed system or becomes a de facto control center: irreversible decision authority, physical resource mobilization authority, and self-expansion authority. The model shows how efficiency pressure, path dependence, scale feedback, and weak boundary constraints concentrate decision-energy in the most efficient node. This concentration can diffuse responsibility and raise the probability of irreversible system-level loss even when local per-action error rates remain low. The main result is a boundary stabilization theorem. It shows that safety need not require proving that advanced systems are always correct. Instead, it requires institutional and technical designs that prevent irreversible power from being released by a single high-efficiency node. The paper reframes AI safety as layered control, authorization, and externally reviewable limits, linking alignment, security engineering, organizational economics, and institutional design.

Wesley Shu, Peng Wei

The Institute of Energetic Paradigm · College of Plant Protection Southwest University, China

AI Control AI Governance Human Oversight of AI AI Safety

May 1, 2026cs.HC

Linking Behaviour and Perception to Evaluate Meaningful Human Control over Partially Automated Driving

Partial driving automation creates a tension: drivers remain legally responsible while being less active in control. Meaningful human control (MHC), a normative framework that can potentially address this tension, proposes that automated systems are designed to track relevant human reasons and that humans should at all times remain in control and be responsible. However, empirical methods for evaluating whether systems are under MHC remain underdeveloped. In this driving simulator study, we investigated the extent to which 24 drivers experienced MHC when interacting with partially automated driving systems under two modes - haptic shared control and traded control. During overtaking manoeuvres on a two-lane, two-way road with fully automated longitudinal control and partially automated lateral control, drivers' actions were necessary to prevent crashes due to silent automation failures. Starting from hypotheses derived from the properties of systems under MHC, we used a mixed-methods approach that links behavioural metrics, subjective post-trial ratings, and qualitative feedback to assess drivers' perception of responsibility and control. A confirmatory analysis indicated a negative correlation between the perception of the automated vehicle understanding the driver and conflict in steering torques. Qualitative feedback revealed that mismatches in intentions between the driver and automation, lack of safety, and resistance to driver inputs reduced perceived MHC, while subtle haptic guidance aligned with driver intent had a positive effect. Thus, future designs should prioritise effortless driver interventions, transparent communication of automation intent through haptic, visual or auditory cues, and clear authority allocation to strengthen meaningful human control in partially automated driving.

Ashwin George, Lucas Elbert Suryana, Lorenzo Flipse +5

Centre for Meaningful Human Control, Delft University of Technology, Mekelweg 2, 2628 CD, Delft, Zuid Holland, The Netherlands · Department of Cognitive Robotics, Delft University of Technology, Mekelweg 2, 2628 CD, Delft, Zuid Holland, The Netherlands · Department of Transport & Planning, Delft University of Technology, Mekelweg 2, 2628 CD, Delft, Zuid Holland, The Netherlands +1

Autonomous Driving Human-in-the-Loop Evaluation Shared Autonomy Human Oversight of AI

Apr 30, 2026cs.AI

Leading Across the Spectrum of Human-AI Relationships: A Conceptual Framework for Increasingly Heterogeneous Teams

What shapes a consequential decision when human and artificial intelligence work on it together? The answer is becoming harder to see. A decision may look human-led after AI has set the frame, or appear automated while human judgment still carries decisive force. This paper offers a leadership-facing spectrum to see those relationships within a bounded mandate: Pure Human, Centaur (human-dominant, with AI in the loop), Co-equal, Minotaur (AI-dominant, with humans in the loop), and Pure AI. The spectrum asks where leadership work occurs: who frames the problem, who redirects the work, and who can answer for what follows. The five positions are landmarks that help leaders recognize configurations as they layer, drift, or change in a single decision. The central risk is misrecognition: leaders may keep a human-centered story in place after decision-shaping authority has shifted elsewhere. They may believe oversight remains meaningful when it has become ceremonial, or keep humans in the loop when their involvement could make the decision worse. The framework introduces co-adaptability, the capacity of a configuration to improve as human and non-human participants adjust together, and places it within heterogeneous teaming, where participants may vary by number, substrate, model architecture, capability, speed, memory, and form of participation. The aim is practical: to help strategic leaders and those designing or deploying AI systems recognize the configuration at work, notice when it shifts, and judge whether it fits the decision before them. These configurations will shape how power, responsibility, and trust are distributed in organizational life. Whether the futures they help create remain governable and worth inhabiting will depend on leaders who can see, early enough, where and how consequential decisions are actually being shaped.

Alejandro R. Jadad

Keck Medical School, University of Southern California & Founder, Vivenxia Group, LLC; Los Angeles, California, USA

Human-AI Decision Making Human Oversight of AI Human-AI Collaboration

Apr 29, 2026cs.CY

Resume-ing Control: (Mis)Perceptions of Agency Around GenAI Use in Recruiting Workflows

When generative AI (genAI) systems are used in high-stakes decision-making, its recommended role is to aid, rather than replace, human decision-making. However, there is little empirical exploration of how professionals making high-stakes decisions, such as those related to employment, perceive their agency and level of control when working with genAI systems. Through interviews with 22 recruiting professionals, we investigate how genAI subtly influences control over everyday workflows and even individual hiring decisions. Our findings highlight a pressing conflict: while recruiters believe they have final authority across the recruiting pipeline, genAI has become an invisible architect that shapes the foundational building blocks of information used for evaluation, from defining a job to determining good interview performances. The decision of whether or not to adopt was also often outside recruiters' control, with many feeling compelled to adopt genAI due to calls to integrate AI from higher-ups in their business, to combat applicant use of AI, and the individual need to boost productivity. Despite a seemingly seismic shift in how recruiting happens, participants only reported marginal efficiency gains. Such gains came at the high cost of recruiter deskilling, a trend that jeopardizes the meaningful oversight of decision-making. We conclude by discussing the implications of such findings for responsible and perceptible genAI use in hiring contexts.

Sajel Surati, Rosanna Bellini, Emily Black

New York University, New York, New York, USA

AI-Assisted Decision Making Human-AI Decision Making Human Oversight of AI

Apr 29, 2026cs.CL

From Black-Box Confidence to Measurable Trust in Clinical AI: A Framework for Evidence, Supervision, and Staged Autonomy

Trust in clinical artificial intelligence (AI) cannot be reduced to model accuracy, fluency of generation, or overall positive user impression. In medicine, trust must be engineered as a measurable system property grounded in evidence, supervision, and operational boundaries of AI autonomy. This article proposes a practical framework for trustworthy clinical AI built around three principles: evidence, supervision, and staged autonomy. Rather than replacing deterministic clinical logic wholesale with end-to-end black-box models, the proposed approach combines a deterministic core, a patient-specific AI assistant for contextual validation, a multi-tier model escalation mechanism, and a human supervision layer for verification, escalation, and risk control. We demonstrate that trust also depends on selective verification of clinically critical findings, bounded clinical context, disciplined prompt architecture, and careful evaluation on realistic cases. Classifier-driven modular prompting is examined as an incremental path to scaling clinical depth without sacrificing prompt performance and without waiting for complete rule-based coverage. To operationalize trust, a set of trust metrics is proposed, built on metrological principles -- measurement uncertainty, calibration, traceability -- enabling quantitative rather than subjective assessment of each architectural layer. In this perspective, trustworthy clinical AI emerges not as a property of an individual model, but as an architectural outcome of a system into which evidence trails, human oversight, tiered escalation, and graduated action rights are embedded from the outset.

Serhii Zabolotnii, Viktoriia Holinko, Olha Antonenko

Cherkasy State Business College, Cherkasy, Ukraine · healthPrecision, New York, NY, USA

Clinical Decision Support Trust in AI Human Oversight of AI Responsible AI

Apr 29, 2026cs.CY

Algorithmic Authority and the Clinical Standard of Care

The integration of artificial intelligence into clinical medicine creates a fundamental tension between algorithmic probabilistic reasoning and the experiential intuition of expert physicians; applying Lawrence Lessig's \enquote{Code is Law} framework, I argue that the architecture of clinical AI systems already functions as de facto medical regulation, reshaping liability and the standard of care. Reframing AI \enquote{hallucination} as structurally analogous to well-documented human cognitive failures such as confirmation bias and premature diagnostic closure, I show that both failure modes demand a unified governance response. I therefore propose a dialectical standard of care that treats the integrated AI-physician dyad as the singular responsible diagnostic entity, mandating the synthesis of algorithmic precision with human interpretive authority within robust data governance and patient privacy frameworks.

Aizierjiang Aiersilan

The George Washington University

AI Accountability Healthcare Clinical Decision-Making AI Governance Human-AI Decision Making Human Oversight of AI

Apr 27, 2026cs.CY

Update Opacity: Epistemic Accessibility and Governance Under AI System Change

Machine learning models embedded in deployed AI systems are routinely updated to maintain correct functioning over time. Yet such updates can generate update opacity: users may not be able to understand why the same input now yields a different output. We argue that update opacity is best understood as a diachronic failure of epistemic accessibility: the problem is that materially relevant changes may fail to remain accessible to human users in forms that support understanding, calibrated reliance, and appropriate action under real role- and time-specific constraints. This makes update opacity a governance problem. Not all change is equally relevant, and disclosing every update would itself undermine use through overload. To address this problem, we combine two complementary governance approaches: the EU AI Act, which helps specify the system-level perimeter of normatively relevant change, and Machine Learning Operations, which provides operational tools for tracking and comparing change over time. On this basis, we propose a framework that models system change through trustworthiness profiles and trustworthiness levels, and uses threshold-based disclosure to surface materially relevant within-envelope change to different stakeholders over time. We illustrate the approach with a medical AI example and derive practical implications for lifecycle documentation, post-market monitoring, and update disclosure.

Andrea Ferrario, Joshua Hatherley

Institute of Biomedical Ethics and History of Medicine, University of Zürich, Zürich, Switzerland · SUPSI, Dalle Molle Institute for Artificial Intelligence (IDSIA), Lugano, Switzerland · ETH Zürich, Zürich, Switzerland +1

AI Governance Human Oversight of AI

Apr 24, 2026cs.AI

A Decoupled Human-in-the-Loop System for Controlled Autonomy in Agentic Workflows

AI agents are increasingly deployed to execute tasks and make decisions within agentic workflows, introducing new requirements for safe and controlled autonomy. Prior work has established the importance of human oversight for ensuring transparency, accountability, and trustworthiness in such systems. However, existing implementations of Human-in-the-Loop (HITL) mechanisms are typically embedded within application logic, limiting reuse, consistency, and scalability across multi-agent environments. This paper presents a decoupled HITL system architecture that treats human oversight as an independent system component within the agent operating environment. The proposed design separates human interaction management from application workflows through explicit interfaces and a structured execution model. In addition, a design framework is introduced to formalize HITL integration along four dimensions: intervention conditions, role resolution, interaction semantics, and communication channel. This framework enables selective and context-aware human involvement while maintaining system-level consistency. The approach supports alignment with emerging agent communication protocols, allowing HITL to be implemented as a protocol-level concern. By externalizing HITL and structuring its integration, the system provides a foundation for scalable governance and progressive autonomy in agentic workflows.

Edward Cheng, Jeshua Cheng

Agentic Workflows Human-in-the-Loop AI AI Agent Governance Human Oversight of AI

Apr 22, 2026cs.AI

Participatory provenance as representational auditing for AI-mediated public consultation

Artificial intelligence is increasingly deployed to synthesize large-scale public input in policy consultations and participatory processes. Yet no formal framework exists for auditing whether these summaries faithfully represent the source population, an accountability gap that existing approaches to AI explainability, grounding and hallucination detection do not address because they focus on output quality rather than input fidelity. Here, participatory provenance is introduced: a measurement framework grounded in optimal transport theory, causal inference and semantic analysis that tracks how individual public submissions are transformed, filtered or lost through AI-mediated summarization. Applied to Canada's 2025-2026 national AI Strategy consultation (

n = 5{,}253

respondents across two independent policy topics), the framework reveals that both official government summaries underperform a random-participant baseline (

-9.1\%

and

-8.0\%

coverage degradation), with

16.9\%

and

15.3\%

of participants effectively excluded. Exclusion concentrates in clusters expressing dissent, scepticism and critique of AI (

33

-

88\%

exclusion rates). Brevity, semantic isolation and rhetorical register independently predict representational outcome. An accompanying open-source interactive tool, the Co-creation Provenance Lab, enables policymakers to audit and iteratively improve summaries, establishing genuine human-in-the-loop oversight at scale.

Sachit Mahajan

Computational Social Science, D-GESS · ETH Zurich, Rämistrasse 101, 8092 Zurich, Switzerland

Data Provenance Algorithmic Auditing Human Oversight of AI

Apr 22, 2026cs.HC

Auditing and Controlling AI Agent Actions in Spreadsheets

Advances in AI agent capabilities have outpaced users' ability to meaningfully oversee their execution. AI agents can perform sophisticated, multi-step knowledge work autonomously from start to finish, yet this process remains effectively inaccessible during execution, often buried within large volumes of intermediate reasoning and outputs: by the time users receive the output, all underlying decisions have already been made without their involvement. This lack of transparency leaves users unable to examine the agent's assumptions, identify errors before they propagate, or redirect execution when it deviates from their intent. The stakes are particularly high in spreadsheet environments, where process and artifact are inseparable. Each decision the agent makes is recorded directly in cells that belong to and reflect on the user. We introduce Pista, a spreadsheet AI agent that decomposes execution into auditable, controllable actions, providing users with visibility into the agent's decision-making process and the capacity to intervene at each step. A formative study (N = 8) and a within-subjects summative evaluation (N = 16) comparing Pista to a baseline agent demonstrated that active participation in execution influenced not only task outcomes but also users' comprehension of the task, their perception of the agent, and their sense of role within the workflow. Users identified their own intent reflected in the agent's actions, detected errors that post-hoc review would have failed to surface, and reported a sense of co-ownership over the resulting output. These findings indicate that meaningful human oversight of AI agents in knowledge work requires not improved post-hoc review mechanisms, but active participation in decisions as they are made.

Sadra Sabouri, Zeinabsadat Saghi, Run Huang +4

University of Southern California Los Angeles, USA · California State Polytechnic University Pomona, USA · Microsoft Redmond, USA

Human-in-the-Loop AI AI Agent Monitoring Human Oversight of AI Spreadsheet Automation Human-AI Collaboration

Apr 21, 2026cs.CY

Agentic Literacy Debt: A Structural Problem the AI Literacy Field Has Not Yet Named

Autonomous AI agents now plan, decide, and act on behalf of users across healthcare, financial services, and workplace contexts, often without step-by-step human approval. Existing AI literacy frameworks were built for a world in which humans evaluate AI outputs and decide whether to act; they have no vocabulary for the user who has delegated decision-making authority to an agent whose actions may not be observable, reversible, or controllable. This paper names the resulting problem agentic literacy debt: the accumulating societal deficit that grows when agentic AI systems are deployed at scale without corresponding literacy infrastructure. The debt compounds through three reinforcing channels (normalization of opaque delegation, multi-agent ecosystem complexity, and institutional path dependence), and it is incurred by the organizations that deploy agents but paid by the users, patients, and citizens on whose behalf the agents act. Evidence from healthcare, financial fraud, and global equity contexts suggests the gap is already consequential. The problem is structural, not a temporary lag that curriculum reform will close. It demands a reframing of AI literacy as a governance capability, not an evaluative one.

Rohith Nama

AI Literacy AI Agent Governance Human Oversight of AI

Apr 18, 2026cs.HC

The Instrumental Dissolution of Typing: Why AI Challenges the Keyboard Era in Knowledge Work

For four decades, the QWERTY keyboard organized white-collar knowledge work. Typing's dominance was instrumental, not cognitively necessary. As multimodal AI achieves human-parity understanding of speech and gesture, this necessity dissolves. We introduce instrumental dissolution -- loss of institutional-default status while persisting in specialist niches. The keyboard era ends not through hardware replacement but through migration of its function into AI systems. The central contribution identifies the verification bottleneck: as AI collapses production friction, the primary constraint shifts from generation to evaluation. Knowledge workers become adversarial auditors rather than keystroke-producers. This restructures professional expertise, organizational communication, and how productive labor is recognized. Converging evidence from history, philosophy, neuroscience, technology, organizational studies, and cultural analysis supports this thesis. We map synthetic literacy -- oral input generating literate output -- as the defining feature of this transition. Under three scenarios (optimistic: 2028-2035; base: 2035-2045; pessimistic: 2045-2060), we specify disconfirmation criteria that would weaken the thesis if observed. We propose seven interface primitives operationalizing verification-centered HCI.

Wei Roy Hua

8T5 Innovations

Human-AI Interaction Human Oversight of AI Human-AI Collaboration

Apr 17, 2026cs.CY

From Consumption to Reflection: Designing Human-AI Relations for Stable Reasoning

Large language models (LLMs) have transformed how humans access information, but not how we reason with it. Their fluency accelerates consumption while bypassing the slow, reflective processes that underpin sound judgment. This paper introduces Relational Reflective Intelligence (RRI), an inference-time governance layer that operationalizes reflection through auditable reasoning loops. RRI operates not inside the model but around it, providing a practical structure for stable, auditable reasoning between humans and LLMs. The core premise is that LLMs inherit cognitive vulnerabilities similar to those that shape human thought: reliance on intuitive shortcuts, confusion between representation and reality, and a preference for coherence over falsification. When humans and models share these tendencies, their errors compound. We refer to this as relational drift, a failure that arises from interaction rather than from the model alone. Addressing this requires a shift from modeling relations between words to structuring relations between model outputs and human reasoning. RRI provides this missing layer through three components: the Rose-Frame, which identifies likely breakdowns in reasoning; the Architect's Pen, which introduces targeted reflection steps at critical moments; and an inference-time workflow that embeds these steps without retraining the model. Together, these elements transform human-AI interaction into a joint reasoning system with explicit checkpoints, conflict surfacing, and an auditable trail of assumptions. Rather than making machines think like humans or forcing humans to reason like machines, RRI creates a structured interaction in which both compensate for each other's limitations. It reframes AI safety as a cognitive architecture problem, where reliable decisions depend on embedding reflection directly into the interaction process.

Rikard Rosenbacke, Carl Rosenbacke, Victor Rosenbacke +1

Faculty of Medicine, Lund University, Sweden · Department of Economics, Lund University School of Economics and Management, Sweden · Department of Health Services Research and Policy, London School of Hygiene & Tropical Medicine, UK

LLM Safety Alignment Human Oversight of AI Human-AI Collaboration

Apr 16, 2026cs.AI

Bureaucratic Silences: What the Canadian AI Register Reveals, Omits, and Obscures

In November 2025, the Government of Canada operationalized its commitment to transparency by releasing its first Federal AI Register. In this paper, we argue that such registers are not neutral mirrors of government activity, but active instruments of ontological design that configure the boundaries of accountability. We analyzed the Register's complete dataset of 409 systems using the Algorithmic Decision-Making Adapted for the Public Sector (ADMAPS) framework, combining quantitative mapping with deductive qualitative coding. Our findings reveal a sharp divergence between the rhetoric of "sovereign AI" and the reality of bureaucratic practice: while 86% of systems are deployed internally for efficiency, the Register systematically obscures the human discretion, training, and uncertainty management required to operate them. By privileging technical descriptions over sociotechnical context, the Register constructs an ontology of AI as "reliable tooling" rather than "contestable decision-making." We conclude that without a shift in design, such transparency artifacts risk automating accountability into a performative compliance exercise, offering visibility without contestability.

Dipto Das, Christelle Tessono, Syed Ishtiaque Ahmed +1

Department of Computer Science · University of Toronto · Toronto, Ontario, Canada +1

Algorithmic Accountability AI Governance Human Oversight of AI

Apr 16, 2026cs.AI

Where are the Humans? A Scoping Review of Fairness in Multi-agent AI Systems

Rapid advances in Generative AI are giving rise to increasingly sophisticated Multi-Agent AI (MAAI) systems. While AI fairness has been extensively studied in traditional predictive scenarios, its examination in MAAI remains nascent and fragmented. This scoping review critically synthesizes existing research on fairness in MAAI systems. Through a qualitative content analysis of 23 selected studies, we identify five archetypal approaches. Our findings reveal that fairness in MAAI systems is often addressed superficially, lacks robust normative foundations, and frequently overlooks the complex dynamics introduced by agent autonomy and system-level interactions. We argue that fairness must be embedded structurally throughout the development lifecycle of MAAI, rather than appended as a post-hoc consideration. Meaningful evaluation requires explicit human oversight, normative clarity, and a precise articulation of fairness objectives and beneficiaries. This review provides a foundation for advancing fairness research in MAAI systems by highlighting critical gaps, exposing prevailing limitations, and suggesting pathways.

Simeon Allmendinger, Luca Deck, Lucas Mueller

University of Bayreuth · Fraunhofer FIT

Algorithmic Fairness Multi-Agent Systems Human Oversight of AI

Apr 16, 2026cs.AI

The Missing Knowledge Layer in AI: A Framework for Stable Human-AI Reasoning

Large language models are increasingly integrated into decision-making in areas such as healthcare, law, finance, engineering, and government. Yet they share a critical limitation: they produce fluent outputs even when their internal reasoning has drifted. A confident answer can conceal uncertainty, speculation, or inconsistency, and small changes in phrasing can lead to different conclusions. This makes LLMs useful assistants but unreliable partners in high-stakes contexts. Humans exhibit a similar weakness, often mistaking fluency for reliability. When a model responds smoothly, users tend to trust it, even when both model and user are drifting together. This paper is the first in a five-paper research series on stabilising human-AI reasoning. The series proposes a two-layer approach: Parts II-IV introduce human-side mechanisms such as uncertainty cues, conflict surfacing, and auditable reasoning traces, while Part V develops a model-side Epistemic Control Loop (ECL) that detects instability and modulates generation accordingly. Together, these layers form a missing operational substrate for governance by increasing signal-to-noise at the point of use. Stabilising interaction makes uncertainty and drift visible before enforcement is applied, enabling more precise capability governance. This aligns with emerging compliance expectations, including the EU AI Act and ISO/IEC 42001, by making reasoning processes traceable under real conditions of use. The central claim is that fluency is not reliability. Without structures that stabilise both human and model reasoning, AI cannot be trusted or governed where it matters most.

Rikard Rosenbacke, Carl Rosenbacke, Victor Rosenbacke +1

Faculty of Medicine, Lund University, Sweden · Department of Economics, Lund University School of Economics and Management, Sweden · Department of Health Services Research and Policy, London School of Hygiene & Tropical Medicine, UK

LLM Uncertainty Estimation AI Governance Human-AI Decision Making Human Oversight of AI

Mar 4, 2026cs.CY

No Certificate, No Categorical Speech Act: A Brouwerian Assertibility Constraint for Public Reason

Generative AI can convert uncertainty into authoritative-seeming verdicts, intensifying the hypersuasive force of automated speech and displacing the justificatory work on which democratic epistemic agency depends. As a corrective, I propose a Brouwer-inspired assertibility constraint for responsible AI: in high-stakes domains, systems may assert or deny claims only if they can provide a publicly inspectable and contestable certificate of entitlement; otherwise they must return Undetermined. This constraint yields a three-status interface semantics (Asserted, Denied, Undetermined) in which statuses mark entitlement to categorical speech rather than truth values of the underlying world-claim. The semantics cleanly separates internal entitlement from public standing while connecting them via the certificate as a boundary object. It also produces a time-indexed entitlement profile that is stable under numerical refinement yet revisable as the public record changes. I operationalize the constraint through decision-layer gating of threshold and argmax decisions, using internal witnesses (e.g., sound bounds or separation margins where available, and contestable surrogates otherwise) and an output contract with reason-coded abstentions. A design lemma shows that any total, certificate-sound binary interface yields witnessed decidability of the deployed predicate on its declared scope, so Undetermined is not a tunable reject option but a mandatory status whenever no adequate forcing witness is available. By making outputs answerable to challengeable warrants rather than confidence alone, the paper aims to preserve epistemic agency against the persuasive pull of automated speech in public justification.

Michael Jülich

aihorizon R&D, Munich, Germany.

AI Accountability Selective Prediction AI Governance Human Oversight of AI Epistemic Uncertainty

Mar 3, 2026cs.GT

Delegation and Verification Under AI

As AI systems enter institutional workflows, workers must decide whether to delegate task execution to AI and how much effort to invest in verifying AI outputs, while institutions evaluate workers using outcome-based standards that may misalign with workers' private costs. We model delegation and verification as the solution to a rational worker's optimization problem, and define worker quality by evaluating an institution-centered utility (distinct from the worker's objective) at the resulting optimal action. We formally characterize optimal worker workflows and show that AI induces phase transitions, where arbitrarily small differences in verification ability lead to sharply different behaviors. As a result, AI can amplify workers with strong verification reliability while degrading institutional worker quality for others who rationally over-delegate and reduce oversight, even when baseline task success improves and no behavioral biases are present. These results identify a structural mechanism by which AI reshapes institutional worker quality and amplifies quality disparities between workers with different verification reliability.

Lingxiao Huang, Wenyang Xiao, Nisheeth K. Vishnoi

Nanjing University · Yale University

Human-in-the-Loop AI Human-AI Decision Making Human Oversight of AI AI and Labor

Jan 21, 2026cs.AI

Agentic AI for Commercial Insurance Underwriting with Adversarial Self-Critique

Commercial insurance underwriting is a labor-intensive process that requires manual review of extensive documentation to assess risk and determine policy pricing. While AI offers substantial efficiency improvements, existing solutions lack comprehensive reasoning and internal mechanisms to ensure reliability in regulated, high-stakes environments. Full automation remains impractical and inadvisable when human judgment and accountability are critical. This study presents a decision-negative, human-in-the-loop agentic system that incorporates an adversarial self-critique mechanism as a bounded safety architecture for regulated underwriting workflows. In this system, a critic agent challenges the primary agent's conclusions prior to submitting recommendations to human reviewers. This internal system of checks and balances addresses a critical gap in AI safety for regulated workflows. Additionally, the research develops a formal taxonomy of failure modes to characterize potential errors by decision-negative agents. This taxonomy provides a structured framework for risk identification and management in high-stakes applications. Experimental evaluation using 500 expert-validated underwriting cases demonstrates that the adversarial critique mechanism reduces AI hallucination rates from 11.3% to 3.8% and increases decision accuracy from 92% to 96%. At the same time, the framework enforces strict human authority over all binding decisions by design. These findings indicate that adversarial self-critique supports safer AI deployment in regulated domains and offers a model for responsible integration where human oversight is indispensable.

Joyjit Roy, Samaresh Kumar Singh

Austin, Texas, USA · Leander, Texas, USA

LLM Self-Correction AI Agent Safety Human Oversight of AI

Nov 10, 2025cs.CY

The Journal of Prompt-Engineered (Moral) Philosophy Or: Why AI-Assisted Ethics Research Requires Process Transparency

Existing AI disclosure mandates in scholarship require that AI assistance be reported but leave transparency philosophically unspecified: they fix the duty without explaining what the duty serves. We argue that ethical inquiry is essentially contested at two independent levels -- about what it is, and about what it demands of the inquirer -- defeating output-only evaluation and welfare-economic dismissal of the transparency question, and, by extension, reproducibility framings imported from the empirical sciences. The transparency duty is grounded instead in agent-integrity: the legibility, before a community of inquiry, of the identity-constituting commitments that the author's mode of philosophising expresses. Because the standards for evaluating such work are not communally settled, the achievable goal for transparency is not evaluation against agreed criteria but tracking -- accumulating the evidentiary record that lets each tradition assess the work on its own terms and makes future normative judgments possible. We develop a documentation-adequacy framework that operationalises Meaningful Human Control through five transparency elements -- declaration, navigation, documentation account, process documentation, and development records -- demonstrated by the paper itself, whose full documentation record is archived at a persistent identifier. The framework is a first iteration subject to revision, not a settled standard.

Michele Loi

University of Milan

AI Accountability Human Oversight of AI

Oct 30, 2025cs.AI

Human-AI Complementarity: A Goal for Amplified Oversight

Human feedback is critical for aligning AI systems to human values. As AI capabilities improve and AI is used to tackle more challenging tasks, verifying quality and safety becomes increasingly challenging. This paper explores how we can leverage AI to improve the quality of human oversight. We focus on an important safety problem that is already challenging for humans: fact-verification of AI outputs. We find that combining AI ratings and human ratings based on AI rater confidence is better than relying on either alone. Giving humans an AI fact-verification assistant further improves their accuracy, but the type of assistance matters. Displaying AI explanation, confidence, and labels leads to over-reliance, but just showing search results and evidence fosters more appropriate trust. These results have implications for Amplified Oversight -- the challenge of combining humans and AI to supervise AI systems even as they surpass human expert performance.

Rishub Jain, Sophie Bridgers, Lili Janzer +3

1Google DeepMind · 2Work done while previously at Google DeepMind

Claim Verification Trust in AI Human Oversight of AI

Oct 4, 2025cs.CY

AI Adoption Across Mission-Driven Organizations

Despite AI's promise, little is known about how mission-driven organizations (MDOs) adopt AI. We conducted semi-structured interviews with 15 experts and leaders within environmental, humanitarian, and development organizations across the Global North and South. We find that MDOs adopt AI selectively, with uses in content creation and data analysis, while maintaining human oversight for mission-critical applications. In case of conflicts between the organization's values and efficiency, participants consider sustainability, neutrality, and community trust as constraints that could limit or prevent AI adoption. Individual adoption of AI is not translated into organizational practice due to fragmented data infrastructure, lack of in-house expertise, inertia, ethical challenges, and dependency on vendors. Participants expected AI use in MDOs to involve institutional control over infrastructure, support for missions, and human-centered human-AI collaboration. We contribute an analysis on how MDOs manage AI adoption, identify barriers to responsible deployment, and provide recommendations for designing mission-aligned AI systems.

Dalia Ali, Muneeb Ahmed, Hailan Wang +6

Technical University of Munich Munich, Germany · Princeton University Princeton, New Jersey, USA · WWF Mumbai, India +1

AI Governance Human Oversight of AI Responsible AI