Overview

Human oversight of AI studies how people retain meaningful authority when systems recommend, automate, or delegate work, and how oversight affects safety, accountability, and human agency. Approaches range from user studies of trust, interfaces, and error detection to formal models for allocating review, selective deferral, uncertainty-aware escalation, and technical controls such as audit logs, permissions, and execution gates. Researchers evaluate these methods in settings including clinical decisions, coding agents, hiring, moderation, education, and safety-critical operations, using benchmarks, simulations, interviews, and workflow studies. A central tension is that greater autonomy can improve speed or performance while making outputs harder to verify and overloading or deskilling the people expected to intervene; the field is working to make oversight effective rather than merely nominal.

Latest papers

CardsList

196 papers20 papers in the last four weeks, up 18% on the four weeks before. 0.2% of all new papers.

  1. Right Diagnosis, Unsafe Route: Auditing Clinical AI Decision Trajectories and Corrective Oversight for Validity and Potential Harm

    Nov 17, 2026Guanqiao Chen, Wei Jiang, Shu Zhang +5Clinical Decision-MakingHuman Oversight of AI

  2. Auditable Authorization for LLM Agents: Empirical Evidence Across Model, Harness, and Workflow Layers

    Nov 14, 2026Bangjie Deng, Xiaoxuan Lu, Wenjun Chen +8AI Agent AuditingHuman Oversight of AI

  3. Between Obligations and Evidence: A Participatory Study of Translating the EU AI Act into Technical Requirements

    Nov 13, 2026Helma Torkamaan, Masoud Mansoury, Yanan Xin +9AI Regulatory ComplianceAI Accountability

  4. When evaluation becomes intervention in clinical AI

    Nov 13, 2026Anthony Abou Mrad, Aviona Conti, Samuel Schmidgall +10LLM-as-a-JudgeClinical Language Model Evaluation

  5. AI-aided Decision-Making in Education - Uncertainty, Explainability, and Human Responsibility

    Nov 13, 2026Fabian Kieser, Paul Tschisgale, Peter WulffAI-Assisted Decision MakingAI in Education

  6. Trust, but verify, audit and attribute: a human-in-the-loop framework for checking AI-produced research results

    Nov 9, 2026György Eigner, Patrik P. Süli, Roland HollósHuman Oversight of AIAI Agent Auditing

  7. When Should AI Overturn a Human Decision? Controversy at the 2026 World Cup and a 2/π\sqrt{2/π} Solution

    Nov 9, 2026Amir Ali Ahmadi, Parsa Alavi, Radeen AlaviHuman-AI Decision MakingHuman Oversight of AI

  8. RADE: Risk-Adjusted Deployment Efficiency, A Framework for Routing, Memory, and Escalation in Safe LLM Systems

    Nov 8, 2026Chaymaa Abbas, Kareem Hassani, Mariette AwadLLM SafetySafety-Utility Trade-Off in Language Models

  9. What to Delegate, What to Preserve: Human Preferences for Agentic AI Across Everyday Life and Work

    Nov 6, 2026Sarah Wheeler, Veronica Rammouz, Yaoyao Qian +5Agentic AIHuman Oversight of AI

  10. Why and How to Do Science When AI Is Better at It: A Framework Grounded in Human Understanding and Direction

    Oct 26, 2026Hoda Heidari, Aydin MohseniAI-Assisted Scientific ResearchHuman Oversight of AI

  11. I-HITL: Inalienable Human-in-the-Loop

    Oct 26, 2026Samuel Breckenridge, Dani Vilardell, Wenhao Wang +2Human-in-the-Loop AIAI Agent Safety

  12. Reliable AI-Assisted Decisions via Selective Auditing

    Oct 22, 2026Isaac Gibbs, Elise L. Han, Ryan J. Tibshirani +1AI-Assisted Decision MakingHuman Oversight of AI

  13. Artificial Intelligence in Mechanical Engineering: Foundations, Opportunities, Challenges, and Responsibilities

    Oct 22, 2026A. Cunha, C. Nataraj, L. M. Lorenzo +3Responsible AIHuman Oversight of AI

  14. Contestable Agents for Data Governance: Recording Human Stewardship of AI-Generated Metadata Across Structured and Unstructured Systems

    Oct 22, 2026Humza Akhtar, Brian FreemanAI Agent GovernanceAI Governance

  15. A Three-Pillar Governance Framework for Safe and Trustworthy AI Agents

    Oct 21, 2026Edward C. Cheng, Jeshua Cheng, Alice SiuAI Agent GovernanceAI Agent Safety

  16. Humans Correct Their Judgments Through Debate, but Weaker AI Models Do Not

    Oct 20, 2026Maria Victoria Carro, Denise Alejandra Mester, Facundo Nieto +14Multi-Agent DebateHuman Oversight of AI

  17. Towards Human-AI Complementarity for AI Safety

    Oct 18, 2026Sander Lanbo Shi, Miranda Anna Christ, Eric Modesitt +20Human-AI ComplementarityHuman Oversight of AI

  18. Following Delegation Traces to Study Human Oversight in Interaction with Multimodal AI

    Oct 15, 2026Agnese Chiatti, Matteo Matteucci, Viola SchiaffonatiHuman Oversight of AIHuman-AI Decision Making

  19. Comprehension Audits to Mitigate Risks from Automated AI Research

    Oct 7, 2026Ronald J. Bodkin, Bahrad A. Sokhansanj, Gillian K. HadfieldHuman Oversight of AIAI Safety

  20. Careful Judge: Safe and Efficient Human-AI Collaborative Decision Making

    Oct 6, 2026Chenyu Zhang, Rachel Luo, Boyi Li +3Human-AI Decision MakingHuman-in-the-Loop AI

  21. A Case Study in Assuring AI-Written Software

    Oct 6, 2026Lindsey Ferris, Sierra BonillaAI Agent ReliabilityAI Assurance

  22. Process Constitutions and Process Stewards: Towards the Next Generation of BPM for Agentic Organizations

    Oct 5, 2026Amin Jalali, Majid RafieiAgentic WorkflowsAI Agent Governance

  23. Dependable AI-Assisted Engineering: A Formal Framework for AI Participation and Assurance in Safety-Critical Workflows

    Oct 2, 2026Puxue TanAI AssuranceHuman Oversight of AI

  24. Feedback Without the Wait: Piloting a Generative AI Practice Platform in a Large Maths Class

    Oct 1, 2026Lili Chen, Gavin Buskes, Yuxin Ren +1Educational AssessmentEducational Technology