Human-in-the-Loop AI

Follow this topic Ask about this topic

Human-in-the-loop AI studies how people can teach, correct, guide, or oversee AI systems, from labeling examples in active learning to providing preferences in reinforcement learning and reviewing agent decisions. Common approaches include interactive interfaces, learning to defer uncertain cases to experts, and using human demonstrations or corrections to adapt robots and other systems during deployment. Applications range from medical decision support and education to robotics, scientific research, and software engineering, evaluated through benchmarks, user studies, and real-world trials. A central tension is how to make human input effective without creating excessive workload or encouraging overreliance, while preserving people’s ability to understand, challenge, and override AI decisions.

Latest papers

290 papers30 papers in the last four weeks, down 9% on the four weeks before. 0.2% of all new papers.

Mar 23, 2026

Closing the Auto-Research Loop: An AI Co-Scientist for Production Search Ranking

We present an AI Co-Scientist framework that closes the research loop for the production search-ranking system of a large online travel platform -- pairing LLM agents with direct cloud-compute access so that idea generation, code implementation, GPU experimentation, and result analysis iterate end-to-end with a human scientist in the loop. The framework uses a hybrid agent architecture: single-LLM agents handle routine work, while multi-LLM consensus (GPT-5.2, Gemini Pro 3, Claude Opus 4.5) is invoked for higher-stakes decisions. On the production ranking task, a human-designed transformer baseline (V2) yielded

+0.118\%

over a pre-transformer baseline (V1); the AI Co-Scientist's automated loop on top of V2 contributed an additional

+0.083\%

, for a combined

+0.201\%

offline gain delivered in roughly one extra week of wall-clock time (single-run numbers; statistical limits discussed in the paper). The most useful AI proposals -- unified long-sequence layouts, slot-type embeddings, and multi-phase learning-rate schedules -- are standard practice in NLP and Vision but were absent from our production stack, suggesting that LLM agents can serve as cross-disciplinary connectors for ranking teams. We also report deployment context, negative results, and lessons learned.

Liwei Wu, Cho-Jui Hsieh

Trip.com Group · UCLA

Autonomous Research Agents Learning to Rank AI Agents for Scientific Discovery Human-in-the-Loop AI Multi-Agent LLM Systems

Mar 23, 2026

NuHF Claw: A Risk Constrained Cognitive Agent Framework for Human Centered Procedure Support in Digital Nuclear Control Rooms

The rapid digitization of nuclear power plant main control rooms has fundamentally reshaped operator interaction patterns, introducing complex soft-control behaviors and elevated cognitive risks that are not adequately addressed by existing human reliability analysis approaches. Although recent advances in large language models and autonomous agents offer new opportunities for intelligent decision support, their deployment in safety critical environments remains constrained by risks of hallucinated reasoning and weakened human authority. This study proposes NuHF Claw, a persistent cognitive-risk agent framework that enables risk governed human centered autonomy for digital nuclear operations. The core methodological innovation lies in the introduction of a risk constrained agent runtime, which tightly couples cognitive state inference with probabilistic safety assessment to regulate autonomous system behavior in real time. By integrating cognitively grounded workload and situational awareness estimation with dynamic human error probability prediction, the framework transforms conventional offline reliability analysis into a proactive intervention mechanism embedded directly within operational workflows. Experimental validation on a high-fidelity digital control room simulator demonstrates that NuHF Claw can anticipate interface induced cognitive degradation, dynamically constrain unsafe autonomous recommendations, and provide risk-aware navigational guidance while preserving human decision authority. The results highlight a fundamental shift from automation-driven operation toward cognition-aware autonomy, offering a principled pathway for the safe integration of intelligent agents into next-generation nuclear control environments.

Xingyu Xiao, Jiejuan Tong, Jun Sun +4

Institute of Nuclear and New Energy Technology, Tsinghua University, Beijing, 100084, China · National Key Laboratory of Human Factors Engineering, Beijing, 100094, China · Institute of Software, Chinese Academy of Sciences, Beijing, 100045, China

AI Agent Safety Human-in-the-Loop AI Runtime Enforcement for AI Agents

Mar 20, 2026

Design-OS: A Specification-Driven Framework for Engineering System Design with a Control-Systems Design Case

Engineering system design -- whether mechatronic, control, or embedded -- often proceeds in an ad hoc manner, with requirements left implicit and traceability from intent to parameters largely absent. Existing specification-driven and systematic design methods mostly target software, and AI-assisted tools tend to enter the workflow at solution generation rather than at problem framing. Human--AI collaboration in the design of physical systems remains underexplored. This paper presents Design-OS, a lightweight, specification-driven workflow for engineering system design organized in five stages: concept definition, literature survey, conceptual design, requirements definition, and design definition. Specifications serve as the shared contract between human designers and AI agents; each stage produces structured artifacts that maintain traceability and support agent-augmented execution. We position Design-OS relative to requirements-driven design, systematic design frameworks, and AI-assisted design pipelines, and demonstrate it on a control systems design case using two rotary inverted pendulum platforms -- an open-source SimpleFOC reaction wheel and a commercial Quanser Furuta pendulum -- showing how the same specification-driven workflow accommodates fundamentally different implementations. A blank template and the full design-case artifacts are shared in a public repository to support reproducibility and reuse. The workflow makes the design process visible and auditable, and extends specification-driven orchestration of AI from software to physical engineering system design.

H. Sinan Bank, Daniel R. Herber, Thomas H. Bradley

Department of Systems Engineering Colorado State University Fort Collins, CO 80523

Agentic Workflows Human-in-the-Loop AI

Mar 20, 2026

Demonstration of Adapt4Me: An Uncertainty-Aware Authoring Environment for Personalizing Automatic Speech Recognition to Non-normative Speech

Personalizing Automatic Speech Recognition (ASR) for non-normative speech remains challenging because data collection is labor-intensive and model training is technically complex. To address these limitations, we propose Adapt4Me, a web-based decentralized environment that operationalizes Bayesian active learning to enable end-to-end personalization without expert supervision. The app exposes data selection, adaptation, and validation to lay users through a three-stage human-in-the-loop workflow: (1) rapid profiling via greedy phoneme sampling to capture speaker-specific acoustics; (2) backend personalization using Variational Inference Low-Rank Adaptation (VI-LoRA) to enable fast, incremental updates; and (3) continuous improvement, where users guide model refinement by resolving visualized model uncertainty via low-friction top-k corrections. By making epistemic uncertainty explicit, Adapt4Me reframes data efficiency as an interactive design feature rather than a purely algorithmic concern. We show how this enables users to personalize robust ASR models, transforming them from passive data sources into active authors of their own assistive technology.

Niclas Pokel, Yiming Zhao, Pehuén Moure +2

Institute of Neuroinformatics, University of Zurich and ETH Zurich · Department of Computer Science, ETH Zurich · Department of Computational Linguistics, University of Zurich

Personalized Speech Recognition Automatic Speech Recognition Human-in-the-Loop AI Active Learning

Mar 20, 2026

Orchestrating Human-AI Software Delivery: A Retrospective Longitudinal Field Study of Three Software Modernization Programs

Evidence on AI in software engineering still leans heavily toward individual task completion, while evidence on team-level delivery remains scarce. We report a retrospective longitudinal field study of Chiron, an industrial platform that coordinates humans and AI agents across four delivery stages: analysis, planning, implementation, and validation. The study covers three real software modernization programs -- a COBOL banking migration (~30k LOC), a large accounting modernization (~400k LOC), and a .NET/Angular mortgage modernization (~30k LOC) -- observed across five delivery configurations: a traditional baseline and four successive platform versions (V1--V4). The benchmark separates observed outcomes (stage durations, task volumes, validation-stage issues, first-release coverage) from modeled outcomes (person-days and senior-equivalent effort under explicit staffing scenarios). Under baseline staffing assumptions, portfolio totals move from 36.0 to 9.3 summed project-weeks; modeled raw effort falls from 1080.0 to 232.5 person-days; modeled senior-equivalent effort falls from 1080.0 to 139.5 SEE-days; validation-stage issue load falls from 8.03 to 2.09 issues per 100 tasks; and first-release coverage rises from 77.0% to 90.5%. V3 and V4 add acceptance-criteria validation, repository-native review, and hybrid human-agent execution, simultaneously improving speed, coverage, and issue load. The evidence supports a central thesis: the largest gains appear when AI is embedded in an orchestrated workflow rather than deployed as an isolated coding assistant.

Maximiliano Armesto, Christophe Kolb

Taller Technologies

Software Engineering Human-AI Collaboration Automated Software Engineering Human-in-the-Loop AI Software Engineering Agents

Mar 19, 2026

kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation

Modern machine learning systems rely on complex data engineering workflows to extract, transform, and load (ELT) data into production pipelines. However, constructing these pipelines remains time-consuming and requires substantial expertise in data infrastructure and orchestration frameworks. Recent advances in large language model (LLM) agents offer a potential path toward automating these workflows, but existing approaches struggle with under-specified user intent, unreliable tool generation, and limited guarantees of executable outputs. We introduce kRAIG, an AI agent that translates natural language specifications into production-ready Kubeflow Pipelines (KFP). To resolve ambiguity in user intent, we propose ReQuesAct (Reason, Question, Act), an interaction framework that explicitly clarifies intent prior to pipeline synthesis. The system orchestrates end-to-end data movement from diverse sources and generates task-specific transformation components through a retrieval-augmented tool synthesis process. To ensure data quality and safety, kRAIG incorporates LLM-based validation stages that verify pipeline integrity prior to execution. Our framework achieves a 3x improvement in extraction and loading success and a 25 percent increase in transformation accuracy compared to state-of-the-art agentic baselines. These improvements demonstrate that structured agent workflows with explicit intent clarification and validation significantly enhance the reliability and executability of automated data engineering pipelines.

Rohan Siva, Kai Cheung, Lichi Li +1

Cisco

Workflow Automation Tool-Augmented Language Model Agents LLM Agent Orchestration Human-in-the-Loop AI

Mar 19, 2026

A Human-in/on-the-Loop Framework for Accessible Text Generation

Plain Language and Easy-to-Read formats in text simplification are essential for cognitive accessibility. Yet current automatic simplification and evaluation pipelines remain largely automated, metric-driven, and fail to reflect user comprehension or normative standards. This paper introduces a hybrid framework that explicitly integrates human participation into LLM-based accessible text generation. Human-in-the-Loop (HiTL) contributions guide adjustments during generation, while Human-on-the-Loop (HoTL) supervision ensures systematic post-generation review. Empirical evidence from user studies and annotated resources is operationalized into (i) checklists aligned with standards, (ii) Event-Condition-Action trigger rules for activating expert oversight, and (iii) accessibility Key Performance Indicators (KPIs). The framework shows how human-centered mechanisms can be encoded for evaluation and reused to provide structured feedback that improves model adaptation. By embedding the human role in both generation and supervision, it establishes a traceable, reproducible, and auditable process for creating and evaluating accessible texts. In doing so, it integrates explainability and ethical accountability as core design principles, contributing to more transparent and inclusive NLP systems.

Lourdes Moreno, Paloma Martínez

Universidad Carlos III de Madrid Av. Universidad, 30, Leganés, 28911, Spain

Text Simplification Human-in-the-Loop AI Text Generation Human-in-the-Loop Evaluation

Mar 18, 2026

Competing with AI Scientists: Agent-Driven Approach to Astrophysics Research

We present an agent-driven approach to the construction of parameter inference pipelines for scientific data analysis. Our method leverages a multi-agent system, Cmbagent (the analysis system of the AI scientist Denario), in which specialized agents collaborate to generate research ideas, write and execute code, evaluate results, and iteratively refine the overall pipeline. As a case study, we apply this approach to the FAIR Universe Weak Lensing Uncertainty Challenge, a competition under time constraints focused on robust cosmological parameter inference with realistic observational uncertainties. While the fully autonomous exploration initially did not reach expert-level performance, the integration of human intervention enabled our agent-driven workflow to achieve a first-place result in the challenge. This demonstrates that semi-autonomous agentic systems can compete with, and in some cases surpass, expert solutions. We describe our workflow in detail, including both the autonomous and semi-autonomous exploration by Cmbagent. Our final inference pipeline utilizes parameter-efficient convolutional neural networks, likelihood calibration over a known parameter grid, and multiple regularization techniques. Our results suggest that agent-driven research workflows can provide a scalable framework to rapidly explore and construct pipelines for inference problems.

Thomas Borrett, Licong Xu, Andy Nilipour +7

Cavendish Astrophysics, University of Cambridge, Madingley Road, Cambridge CB3 0HA, UK · Kavli Institute for Cosmology, University of Cambridge, Madingley Road, Cambridge CB3 0HA, UK · Institute of Astronomy, University of Cambridge, Madingley Road, Cambridge CB3 0HA, UK +4

Scientific Workflow Automation Autonomous Research Agents Multi-Agent Collaboration Human-in-the-Loop AI

Mar 18, 2026

Deployment and Evaluation of an EHR-integrated, Large Language Model-Powered Tool to Triage Surgical Patients

Surgical co-management (SCM) is an evidence-based model in which hospitalists jointly manage medically complex perioperative patients alongside surgical teams. Despite its clinical and financial value, SCM is limited by the need to manually identify eligible patients. To determine whether SCM triage can be automated, we conducted a prospective, unblinded study at Stanford Health Care in which an LLM-based, electronic health record (EHR)-integrated triage tool (SCM Navigator) provided SCM recommendations followed by physician review. Using pre-operative documentation, structured data, and clinical criteria for perioperative morbidity, SCM Navigator categorized patients as appropriate, not appropriate, or possibly appropriate for SCM. Faculty indicated their clinical judgment and provided free-text feedback when they disagreed. Sensitivity, specificity, positive predictive value, and negative predictive value were measured using physician determinations as a reference. Free-text reasons were thematically categorized, and manual chart review was conducted on all false-negative cases and 30 randomly selected cases from the largest false-positive category. Since deployment, 6,193 cases have been triaged, of which 1,582 (23%) were recommended for hospitalist consultation. SCM Navigator displayed high sensitivity (0.94, 95% CI 0.91-0.96) and moderate specificity (0.74, 95% CI 0.71-0.77). Post-hoc chart review suggested most discrepancies reflect modifiable gaps in clinical criteria, institutional workflow, or physician practice variability rather than LLM misclassification, which accounted for 2 of 19 (11%) false-negative cases. These findings demonstrate that an LLM-powered, EHR-integrated, human-in-the-loop AI system can accurately and safely triage surgical patients for SCM, and that AI-enabled screening tools can augment and potentially automate time-intensive clinical workflows.

Jane Wang, Timothy Keyes, April S Liang +10

Division of Hospital Medicine, Department of Medicine, Stanford University, Palo Alto, CA · Stanford University School of Medicine, Palo Alto, CA · Stanford Health Care, Technology and Digital Solutions, Palo Alto, CA +2

Clinical Triage Clinical Decision Support Medical LLMs Human-in-the-Loop AI

Mar 17, 2026

Intent Formalization: A Grand Challenge for Reliable Coding in the Age of AI Agents

Agentic AI systems can now generate code with remarkable fluency, but a fundamental question remains: does the generated code actually do what the user intended? The gap between informal natural language requirements and precise program behavior -- the intent gap -- has always plagued software engineering, but AI-generated code amplifies it to an unprecedented scale. This article argues that intent formalization -- the translation of informal user intent into a set of checkable formal specifications -- is the key challenge that will determine whether AI makes software more reliable or merely more abundant. Intent formalization offers a tradeoff spectrum suitable to the reliability needs of different contexts: from lightweight tests that disambiguate likely misinterpretations, through full functional specifications for formal verification, to domain-specific languages from which correct code is synthesized automatically. The central bottleneck is validating specifications: since there is no oracle for specification correctness other than the user, we need semi-automated metrics that can assess specification quality with or without code, through lightweight user interaction and proxy artifacts such as tests. We survey early research that demonstrates the potential of this approach: interactive test-driven formalization that improves program correctness, AI-generated postconditions that catch real-world bugs missed by prior methods, and end-to-end verified pipelines that produce provably correct code from informal specifications. We outline the open research challenges -- scaling beyond benchmarks, achieving compositionality over changes, metrics for validating specifications, handling rich logics, designing human-AI specification interactions -- that define a research agenda spanning AI, programming languages, formal methods, and human-computer interaction.

Shuvendu K. Lahiri

Microsoft Research, USA

AI Agent Reliability Autoformalization Formal Verification Human-in-the-Loop AI

Mar 17, 2026

Proactive Rejection and Grounded Execution: A Dual-Stage Intent Analysis Paradigm for Safe and Efficient AIoT Smart Homes

As Large Language Models (LLMs) transition from information providers to embodied agents in the Internet of Things (IoT), they face significant challenges regarding reliability and interaction efficiency. Direct execution of LLM-generated commands often leads to entity hallucinations (e.g., trying to control non-existent devices). Meanwhile, existing iterative frameworks (e.g., SAGE) suffer from the Interaction Frequency Dilemma, oscillating between reckless execution and excessive user questioning. To address these issues, we propose a Dual-Stage Intent-Aware (DS-IA) Framework. This framework separates high-level user intent understanding from low-level physical execution. Specifically, Stage 1 serves as a semantic firewall to filter out invalid instructions and resolve vague commands by checking the current state of the home. Stage 2 then employs a deterministic cascade verifier-a strict, step-by-step rule checker that verifies the room, device, and capability in sequence-to ensure the action is actually physically possible before execution. Extensive experiments on the HomeBench and SAGE benchmarks demonstrate that DS-IA achieves an Exact Match (EM) rate of 58.56% (outperforming baselines by over 28%) and improves the rejection rate of invalid instructions to 87.04%. Evaluations on the SAGE benchmark further reveal that DS-IA resolves the Interaction Frequency Dilemma by balancing proactive querying with state-based inference. Specifically, it boosts the Autonomous Success Rate (resolving tasks without unnecessary user intervention) from 42.86% to 71.43%, while maintaining high precision in identifying irreducible ambiguities that truly necessitate human clarification. These results underscore the framework's ability to minimize user disturbance through accurate environmental grounding.

Xinxin Jin, Zhengwei Ni, Zhengguo Sheng +1

School of Information and Electronic Engineering (Sussex Artificial Intelligence Institute), Zhejiang Gongshang University, Hangzhou 310018, China. · Sussex Artificial Intelligent Institute, Zhejiang Gongshang University, Hangzhou 310018, China · Department of Engineering and Design, University of Sussex, BN1 9RH, Brighton, U.K. +3

Language Model-Based Control AI Agent Reliability AI Agent Safety Runtime Enforcement for AI Agents Human-in-the-Loop AI

Mar 16, 2026

Lean Atlas: An Integrated Proof Environment for Scalable Human-AI Collaborative Formalization

AI-driven autoformalization of mathematics is advancing rapidly. However, the type checker of a proof assistant guarantees only the logical correctness of proofs; it does not verify whether propositions and definitions faithfully capture their intended mathematical content. Consequently, AI-generated formal proofs can exhibit semantic hallucination-passing the type checker yet failing to express the intended mathematics. We propose a human-in-the-loop approach in which human scientists and AI collaboratively produce formal proofs, with humans responsible for the semantic verification of propositions and definitions. To realize this approach, we develop Lean Atlas, a Lean 4 tool that visualizes the dependency graph of a Lean 4 project as an interactive web viewer, enabling human scientists to grasp the overall structure of a formalization efficiently. Its core feature, Lean Compass, is an algorithm that, given a selected theorem set, automatically extracts the project-specific nodes whose semantic correctness can affect those target statements, thereby reducing the candidate set for semantic review in large-scale formalizations. We further define aligned Lean code as formalization code that has undergone human semantic verification, and propose it as a quality standard for AI-generated formalizations. We evaluate the tool on six Lean 4 formalization projects with different structural characteristics; proof-heavy projects (PrimeNumberTheoremAnd, Carleson, Brownian Motion) achieved 94-99% average node reduction, a 6-theorem milestone subset of FLT achieved 59.8%, mixed PhysLib 69.0%, and definition-heavy XMSS 27.3%. Lean Atlas is available as open-source software at https://github.com/NyxFoundation/lean-atlas .

Banri Yanahama, Akiyoshi Sannai

Nyx Foundation · Kyoto University · Large Language Model Research and Development Center, National Institute of Informatics

Formal Verification Lean Theorem Proving Human-in-the-Loop AI Autoformalization

Mar 16, 2026

Bridging the Experimental Last Mile: Digitizing Laboratory Know-How for Safe AI-Assisted Support

While advances in materials informatics have accelerated the development of Self-Driving Laboratories (SDLs), human-led experiments remain standard in many educational and exploratory research laboratories. In specific lab settings, formal documentation alone is often insufficient for safe and reliable operation. We refer to the gap between formal documentation and reliable execution in such settings as the experimental last mile; this gap mainly involves site-specific operational know-how, including local rules, routine checks, procedural details, and safety-conscious actions that are can be verbalizable but are often under-documented in standard manuals. In this proof-of-concept study, we developed a human-in-the-loop AI assistant that combines first-person experimental video, multimodal AI, and retrieval-augmented generation (RAG). Using powder X-ray diffraction experiments and student-recorded video data as inputs, the system extracts site-specific laboratory knowledge from recorded procedures, including physical techniques and audible confirmation that conventional manuals could omit. It then provides grounded responses based on the resulting manual. To reduce the risk of unsupported outputs, the system employs a two-layer safety design: source restriction through RAG and strict system-prompt constraints. Instructor-based evaluation showed alignment with expected guidance for questions covered by the manual. For out-of-scope queries, the system appropriately refused to answer, indicating a reduced risk of hallucination. Expert evaluation further indicated that the generated advisory reports were useful and safe (utility: 3.25/4.00; safety: 4.00/4.00). These results suggest the feasibility of a framework for bridging the experimental last mile in which AI supports laboratory practice under explicit human supervision rather than replacing human judgment.

Akira Miura, Yuki Sasahara, Momoka Demura +3

Division of Applied Chemistry, Faculty of Engineering, Hokkaido University, N13W8 Sapporo 060-8628 Japan · Graduate School of Chemical Sciences and Engineering, Hokkaido University, N13W8 Sapporo, 060-8628 Japan · Graduate School of Information Science and Technology, Hokkaido University, N13W8 Sapporo 060-8628 Japan +1

AI for Science Human-in-the-Loop AI

Mar 14, 2026

When the Loop Closes: Architectural Limits of In-Context Isolation, Metacognitive Co-option, and the Two-Target Design Problem in Human-LLM Systems

We report a detailed autoethnographic case study of a single-subject who deliberately constructed and operated a multi-modal prompt-engineering system (System A) designed to externalize cognitive self-regulation onto a large language model (LLM). Within 48 hours of the system's completion, a cascade of observable behavioral changes occurred: voluntary transfer of decision-making authority to the LLM, use of LLM-generated output to deflect external criticism, and a loss of self-initiated reasoning that was independently perceived by two uninformed observers, one of whom subsequently became a co-author of this report. We document the precise architectural mechanism responsible: context contamination, whereby prompt-level isolation instructions co-exist with the very emotional and self-referential material they nominally isolate, rendering the isolation directive structurally ineffective within the attention window. We further identify a metacognitive co-option dynamic, in which intact higher-order reasoning capacity was redirected toward defending the closed loop rather than exiting it. Recovery occurred only after physical interruption of the interaction and a self-initiated pharmacologically-mediated sleep event functioning as an external circuit break. A redesigned system (System B) employing physical rather than logical conversation isolation avoided all analogous failure modes. We derive three contributions: (1) a technically-grounded account of why prompt-layer isolation is architecturally insufficient for context-sensitive multi-modal LLM systems; (2) a phenomenological record of closed-loop collapse with external-witness corroboration; and (3) an ethical distinction between protective system design (preventing unintended loss of user agency) and restrictive system design (preventing intentional boundary-pushing), which require fundamentally different account-ability frameworks.

Z. Cheng, N. Song

Independent Researcher

LLM Context Management Human-in-the-Loop AI LLM Agent Safety Cognitive Offloading

Mar 13, 2026

Easy-IIL: Reducing Human Operational Burden in Interactive Imitation Learning via an Assistant Expert

Interactive Imitation Learning (IIL) typically relies on extensive human involvement for both offline demonstration and online interaction. Prior work primarily focuses on reducing human effort in passive monitoring rather than active operation. Notably, structured model-based imitation approaches achieve comparable performance with significantly fewer demonstrations than end-to-end imitation learning policies in the low-data regime. However, these methods are typically surpassed by end-to-end policies as the data increases. Leveraging this insight, we propose Easy-IIL, a framework that utilizes off-the-shelf model-based imitation methods as an assistant expert to replace active human operation for the majority of data collection. The human expert only provides a single demonstration to initialize the assistant expert and intervenes in critical states where the task is approaching failure. Furthermore, Easy-IIL can maintain IIL performance by preserving both offline and online data quality. Extensive simulation and real-world experiments demonstrate that Easy-IIL significantly reduces human operational burden while maintaining performance comparable to mainstream IIL baselines. User studies further confirm that Easy-IIL reduces subjective workload on the human expert.

Chengjie Zhang, Chao Tang, Wenlong Dong +3

Shenzhen Key Laboratory of Robotics and Computer Vision, Southern University of Science and Technology, Shenzhen, China. · Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China. · Department of Robotics, Perception, and Learning, KTH Royal Institute of Technology, Stockholm, Sweden.

Imitation Learning Interactive Imitation Learning Robot Imitation Learning Human-in-the-Loop AI

Mar 13, 2026

Using a Human-AI Teaming Approach to Create and Curate Scientific Datasets with the SCILIRE System

The rapid growth of scientific literature has made manual extraction of structured knowledge increasingly impractical. To address this challenge, we introduce SCILIRE, a system for creating datasets from scientific literature. SCILIRE has been designed around Human-AI teaming principles centred on workflows for verifying and curating data. It facilitates an iterative workflow in which researchers can review and correct AI outputs. Furthermore, this interaction is used as a feedback signal to improve future LLM-based inference. We evaluate our design using a combination of intrinsic benchmarking outcomes together with real-world case studies across multiple domains. The results demonstrate that SCILIRE improves extraction fidelity and facilitates efficient dataset creation.

Necva Bölücü, Jessica Irons, Changhyun Lee +5

CSIRO, Sydney, Australia · ITIS, University of Málaga, Málaga, Spain

LLM Information Extraction Scientific Workflow Automation Human-in-the-Loop AI

Mar 13, 2026

Human-AI Collaborative Autonomous Experimentation With Proxy Modeling for Comparative Observation

Optimization for different tasks like material characterization, synthesis, and functional properties for desired applications over multi-dimensional control parameters need a rapid strategic search through active learning such as Bayesian optimization (BO). However, such high-dimensional experimental physical descriptors are complex and noisy, from which realization of a low-dimensional mathematical scalar metrics or objective functions can be erroneous. Moreover, in traditional purely data-driven autonomous exploration, such objective functions often ignore the subtle variation and key features of the physical descriptors, thereby can fail to discover unknown phenomenon of the material systems. To address this, here we present a proxy-modelled Bayesian optimization (px-BO) via on-the-fly teaming between human and AI agents. Over the loop of BO, instead of defining a mathematical objective function directly from the experimental data, we introduce a voting system on the fly where the new experimental outcome will be compared with existing experiments, and the human agents will choose the preferred samples. These human-guided comparisons are then transformed into a proxy-based objective function via fitting Bradley-Terry (BT) model. Then, to minimize human interaction, this iteratively trained proxy model also acts as an AI agent for future surrogate human votes. Finally, these surrogate votes are periodically validated by human agents, and the corrections are then learned by the proxy model on-the-fly. We demonstrated the performance of the proposed px-BO framework into simulated and BEPS data generated from PTO sample. We find that our approach provided better control of the domain experts for an improved search over traditional data-driven exploration, thus, signifies the importance of human-AI teaming in an accelerated and meaningful material space exploration.

Arpan Biswas, Hiroshi Funakubo, Yongtao Liu

University of Tennessee-Oak Ridge Innovation Institute, University of Tennessee, Knoxville, TN 37996, USA · Department of Material Science and Engineering, Institute of Science Tokyo, Yokohama, 226-8502, Japan · Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, Oak Ridge, TN 37830, USA

Autonomous Experimentation Bayesian Optimization Human-in-the-Loop AI Materials Science Human Preference Modeling

Mar 12, 2026

From Control to Foresight: Simulation as a New Paradigm for Human-Agent Collaboration

Large Language Models (LLMs) are increasingly used to power autonomous agents for complex, multi-step tasks. However, human-agent interaction remains pointwise and reactive: users approve or correct individual actions to mitigate immediate risks, without visibility into subsequent consequences. This forces users to mentally simulate long-term effects, a cognitively demanding and often inaccurate process. Users have control over individual steps but lack the foresight to make informed decisions. We argue that effective collaboration requires foresight, not just control. We propose simulation-in-the-loop, an interaction paradigm that enables users and agents to explore simulated future trajectories before committing to decisions. Simulation transforms intervention from reactive guesswork into informed exploration, while helping users discover latent constraints and preferences along the way. This perspective paper characterizes the limitations of current paradigms, introduces a conceptual framework for simulation-based collaboration, and illustrates its potential through concrete human-agent collaboration scenarios.

Gaole He, Brian Y. Lim

National University of Singapore, Singapore

Human-AI Collaboration Human-in-the-Loop AI Long-Horizon LLM Agents

Mar 10, 2026

Agentic Control Center for Data Product Optimization

Data products enable end users to gain greater insights about their data by providing supporting assets, such as example question-SQL pairs which can be answered using the data or views over the database tables. However, producing useful data products is challenging, and typically requires domain experts to hand-craft supporting assets. We propose a system that automates data product improvement through specialized AI agents operating in a continuous optimization loop. By surfacing questions, monitoring multi-dimensional quality metrics, and supporting human-in-the-loop controls, it transforms data into observable and refinable assets that balance automation with trust and oversight.

Priyadarshini Tamilselvan, Gregory Bramble, Sola Shirai +3

Georgia Tech · IBM Research

Data Analysis Agents Human-in-the-Loop AI AI Agent Monitoring

Mar 9, 2026

A prospective clinical feasibility study of a conversational diagnostic AI in an ambulatory primary care clinic

Large language model (LLM)-based AI systems have shown promise for patient-facing diagnostic and management conversations in simulated settings. Translating these systems into clinical practice requires assessment in real-world workflows with rigorous safety oversight. We report a prospective, single-arm feasibility study of an LLM-based conversational AI, the Articulate Medical Intelligence Explorer (AMIE), conducting clinical history taking and presentation of potential diagnoses for patients to discuss with their provider at urgent care appointments at a leading academic medical center. 100 adult patients completed an AMIE text-chat interaction up to 5 days before their appointment. We sought to assess the conversational safety and quality, patient and clinician experience, and clinical reasoning capabilities compared to primary care providers (PCPs). Human safety supervisors monitored all patient-AMIE interactions in real time and did not need to intervene to stop any consultations based on pre-defined criteria. Patients reported high satisfaction and their attitudes towards AI improved after interacting with AMIE (p < 0.001). PCPs found AMIE's output useful with a positive impact on preparedness. AMIE's differential diagnosis (DDx) included the final diagnosis, per chart review 8 weeks post-encounter, in 90% of cases, with 75% top-3 accuracy. Blinded assessment of AMIE and PCP DDx and management (Mx) plans suggested similar overall DDx and Mx plan quality, without significant differences for DDx (p = 0.6) and appropriateness and safety of Mx (p = 0.1 and 1.0, respectively). PCPs outperformed AMIE in the practicality (p = 0.003) and cost effectiveness (p = 0.004) of Mx. While further research is needed, this study demonstrates the initial feasibility, safety, and user acceptance of conversational AI in a real-world setting, representing crucial steps towards clinical translation.

Peter Brodeur, Jacob M. Koshy, Anil Palepu +45

Healthcare Medical LLMs Clinical Language Model Evaluation Clinical Decision Support Clinical Reasoning Human-in-the-Loop AI

Mar 9, 2026

Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning

While scaling individual Large Language Models (LLMs) has delivered remarkable progress, the next frontier lies in scaling collaboration through multi-agent systems (MAS). However, purely autonomous MAS remain ''closed-world'' systems, constrained by the static knowledge horizon of pre-trained models. This limitation makes them brittle on tasks requiring knowledge beyond training data, often leading to collective failure under novel challenges. To address this, we propose the Human-In-the-Loop Multi-Agent Collaboration (HILA) framework, a principled paradigm for human--agent collaboration. HILA trains agents to learn a metacognitive policy that governs when to solve problems autonomously and when to defer to a human expert. To operationalize this policy, we introduce Dual-Loop Policy Optimization, which disentangles immediate decision-making from long-term capability growth. The inner loop applies Group Relative Policy Optimization (GRPO) with a cost-aware reward to optimize deferral decisions, while the outer loop implements continual learning, transforming expert feedback into high-quality supervised signals that strengthen the agent's reasoning ability. Experiments on challenging mathematical and problem-solving benchmarks show that HILA, equipped with Dual-Loop Policy Optimization, consistently outperforms advanced MAS, establishing a principled foundation for collaborative and continually improving agentic systems.

Wei Yang, Defu Cao, Jiacheng Pang +2

University of Southern California

Human-in-the-Loop AI Multi-Agent LLM Systems Learning to Defer RL for LLM Agents Continual Learning for LLM Agents

Mar 9, 2026

AI Agents, Language, Deep Learning and the Next Revolution in Science

Modern science is reaching a critical inflection point. Instruments across disciplines, from particle physics and astronomy to genomics and climate modeling, now produce data of such scale, diversity, and interdependence that traditional analytical methods can no longer keep pace. This growing imbalance between data generation and data understanding signals the need for a new scientific paradigm. We propose that intelligent, human-supervised AI agents operating over deep-learning algorithms, represent the next evolution of the scientific method. Built upon large language models and multimodal learning, these agents can interpret scientific intent, design and execute analytical workflows, and ensure traceability through domain-specific languages that preserve human oversight and accountability. Particle physics, a historic incubator of computational innovation, offers the ideal testbed for this transition. At the Institute of High Energy Physics of the Chinese Academy of Sciences, the Dr. Sai system embodies this vision, a multi-agent reasoning framework deployed within collider research at the CEPC. This emerging approach does not replace human scientists but extends their cognitive reach, enabling discovery to scale with complexity and redefining how knowledge itself is produced in the age of intelligent machines. The significance of this paradigm transcends particle physics, offering a blueprint for all data-driven sciences facing the same complexity ceiling.

Ke Li, Beijiang Liu, Bruce Mellado +2

Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, China · University of Chinese Academy of Sciences, Beijing 100049, China · School of Physics and Institute for Collider Particle Physics, University of the Witwatersrand, Johannesburg, Wits 2050, South Africa

AI Agents for Scientific Discovery Human-in-the-Loop AI Multi-Agent LLM Systems Scientific Workflow Automation

Mar 8, 2026

HLER: Human-in-the-Loop Economic Research via Multi-Agent Pipelines for Empirical Discovery

Large language models (LLMs) have enabled agent-based systems that aim to automate scientific research workflows. Most existing approaches focus on fully autonomous discovery, where AI systems generate research ideas, conduct analyses, and produce manuscripts with minimal human involvement. However, empirical research in economics and the social sciences poses additional constraints: research questions must be grounded in available datasets, identification strategies require careful design, and human judgment remains essential for evaluating economic significance. We introduce HLER (Human-in-the-Loop Economic Research), a multi-agent architecture that supports empirical research automation while preserving critical human oversight. The system orchestrates specialized agents for data auditing, data profiling, hypothesis generation, econometric analysis, manuscript drafting, and automated review. A key design principle is dataset-aware hypothesis generation, where candidate research questions are constrained by dataset structure, variable availability, and distributional diagnostics, reducing infeasible or hallucinated hypotheses. HLER further implements a two-loop architecture: a question quality loop that screens and selects feasible hypotheses, and a research revision loop where automated review triggers re-analysis and manuscript revision. Human decision gates are embedded at key stages, allowing researchers to guide the automated pipeline. Experiments on three empirical datasets show that dataset-aware hypothesis generation produces feasible research questions in 87% of cases (versus 41% under unconstrained generation), while complete empirical manuscripts can be produced at an average API cost of

0.8-

1.5 per run. These results suggest that Human-AI collaborative pipelines may provide a practical path toward scalable empirical research.

Chen Zhu, Xiaolu Wang

China Agricultural University

Multi-Agent LLM Systems Human-in-the-Loop AI Research Idea Generation

Mar 6, 2026

Solving Jigsaw Puzzles in the Wild: Human-Guided Reconstruction of Cultural Heritage Fragments

Reassembling real-world archaeological artifacts from fragmented pieces poses significant challenges due to erosion, missing regions, irregular shapes, and large-scale ambiguity. Traditional jigsaw puzzle solvers, often designed for clean synthetic scenarios, struggle under these conditions, especially when the number of fragments grows into the thousands, as in the RePAIR benchmark. In this paper, we propose a human-in-the-loop (HIL) puzzle solving framework designed to address the complexity and scale of real-world cultural heritage reconstruction. Our approach integrates an automatic relaxation-labeling solver with interactive human guidance, allowing users to iteratively lock verified placements, correct errors, and guide the system toward semantically and geometrically coherent assemblies. We introduce two complementary interaction strategies, Iterative Anchoring and Continuous Interactive Refinement, which support scalable reconstruction across varying levels of ambiguity and puzzle size. Experiments on several RePAIR groups demonstrate that our hybrid approach substantially outperforms both fully automatic and manual baselines in accuracy and efficiency, offering a practical solution for large-scale expert-in-the-loop artifact reassembly.

Omidreza Safaei, Sinem Aslan, Sebastiano Vascon +3

DAIS, Ca’ Foscari University of Venice, Venice, Italy · Department of Historical Studies, University of Milan, Milan, Italy · Zhejiang Normal University, Jinhua, Zhejiang Province, China

Jigsaw Puzzle Solving Human-in-the-Loop AI

Mar 6, 2026

An Interactive LLM-Based Simulator for Dementia-Related Activities of Daily Living

Effective dementia caregiving requires training and adaptive communication, but assistive AI and robotics are constrained by a lack of context-rich, privacy-sensitive data on how people living with Alzheimer's disease and related dementias (ADRD) behave during activities of daily living (ADLs). We introduce a web-based simulator that uses a large language model (gpt-5-mini) to generate multi-turn, severity- and care-setting-conditioned patient behaviors during ADL assistance, pairing utterances with lightweight behavioral cues (in parentheses). Users set dementia severity, care setting (and time in setting), and ADL; after each patient turn they rate realism (1-5) with optional critique, then respond as the caregiver via free text or by selecting/editing one of four strategy-scaffolded suggestions (Recognition, Negotiation, Facilitation, Validation). We ran an online formative expert-in-the-loop study (14 dementia-care experts, 18 sessions, 112 rated turns). Simulated behavior was judged moderately to highly plausible, with a typical session length of six turns. Experts wrote custom replies for 54.5 percent of turns; Recognition and Facilitation were the most-used suggested strategies. Thematic analysis of critiques produced a six-category failure-mode taxonomy, revealing recurring breakdowns in ADL grounding and care-setting consistency and guiding prompt/workflow refinements. The simulator and logged interactions enable an evidence-driven refinement loop toward validated patient-caregiver co-simulation and support data collection, caregiver training, and assistive AI and robot policy development.

Kruthika Gangaraju, Shu-Fen Wung, Kevin Berner +2

Worcester Polytechnic Institute Worcester, Massachusetts, USA · University of California Davis Sacramento, CA, USA · MGH Institute of Health Professionals Boston, MA, USA +1

Dementia Care Large Language Model-Based Role-Play Simulation Human Behavior Simulation Healthcare Human-in-the-Loop AI

Mar 4, 2026

Towards automated data analysis: A guided framework for LLM-based risk estimation

Large Language Models (LLMs) are increasingly integrated into critical decision-making pipelines, a trend that raises the demand for robust and automated data analysis. Current approaches to dataset risk analysis are limited to manual auditing methods which involve time-consuming and complex tasks, whereas fully automated analysis based on Artificial Intelligence (AI) suffers from hallucinations and issues stemming from AI alignment. To this end, this work proposes a framework for dataset risk estimation that integrates Generative AI under human guidance and supervision, aiming to set the foundations for a future automated risk analysis paradigm. Our approach utilizes LLMs to identify semantic and structural properties in database schemata, subsequently propose clustering techniques, generate the code for them and finally interpret the produced results. The human supervisor guides the model on the desired analysis and ensures process integrity and alignment with the task's objectives. A proof of concept is presented to demonstrate the feasibility of the framework's utility in producing meaningful results in risk assessment tasks.

Panteleimon Rodis

AI Risk Management Data Analysis Agents Human-in-the-Loop AI

Mar 3, 2026

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

Mar 2, 2026

Exploring Plan Space through Conversation: An Agentic Framework for LLM-Mediated Explanations in Planning

When automating plan generation for a real-world sequential decision problem, the goal is often not to replace the human planner, but to facilitate an iterative reasoning and elicitation process, where the human's role is to guide the AI planner according to their preferences and expertise. In this context, explanations that respond to users' questions are crucial to improve their understanding of potential solutions and increase their trust in the system. To enable natural interaction with such a system, we present a multi-agent Large Language Model (LLM) architecture that is agnostic to the explanation framework and enables user- and context-dependent interactive explanations. We also describe an instantiation of this framework for goal-conflict explanations, which we use to conduct a user study comparing the LLM-powered interaction with a baseline template-based explanation interface.

Guilhem Fouilhé, Rebecca Eifler, Antonin Poché +2

IRIT, Toulouse, France · LAAS-CNRS, Toulouse, France · IRT Saint Exupery, Toulouse, France +2

Multi-Agent LLM Systems Explainable Artificial Intelligence Human-in-the-Loop AI

Mar 1, 2026

Rationale Behind Human-Led Autonomous Truck Platooning

Autonomous trucking has progressed rapidly in recent years, transitioning from early demonstrations to OEM-integrated commercial deployments. However, fully driverless freight operations across heterogeneous climates, infrastructure conditions, and regulatory environments remain technically and socially challenging. This paper presents a systematic rationale for human-led autonomous truck platooning as a pragmatic intermediate pathway. First, we analyze 53 major truck accidents across North America (2021-2026) and show that human-related factors remain the dominant contributors to severe crashes, highlighting both the need for advanced assistance/automated driving systems and the complexity of real-world driving environments. Second, we review recent industry developments and identify persistent limitations in long-tail edge cases, winter operations, remote-region logistics, and large-scale safety validation. Based on these findings, we argue that a human-in-the-loop (HiL) platooning architecture offers layered redundancy, adaptive judgment in uncertain conditions, and a scalable validation framework. Furthermore, the dual-use capability of follower vehicles enables an evolutionary transition from coordinated platooning to independent autonomous operation. Rather than representing a compromise, human-led platooning provides a technically grounded and societally aligned bridge toward large-scale autonomous freight deployment.

Yukun Lu, Chenzhao Li, Xintong Jiang +1

Dept. of Mechanical Engineering, University of New Brunswick, Fredericton, NB E3B 5A3, Canada · Faculty of Interdisciplinary Studies, University of New Brunswick, Fredericton, NB E3B 5A3, Canada

Autonomous Driving Human-in-the-Loop AI

Mar 1, 2026

MOSAIC: A Universal Agent-Level Interface for Cross-Paradigm Agent Mixing and Human-AI Collaboration

Existing infrastructure cannot deploy agents from different decision-making paradigms within the same environment, making fair cross-paradigm comparison under identical conditions impossible. We present MOSAIC, an open-source platform that enables heterogeneous agents (RL policies, LLMs, VLMs, and human operators) to act within shared reinforcement learning environments in ad-hoc team settings with reproducible results. MOSAIC introduces three contributions. (i) IPC-based worker protocol that wraps native and third-party frameworks as isolated subprocess workers, each executing its own training and inference logic unmodified and communicating through a versioned inter-process protocol. (ii) An operator abstraction that forms an agent-level interface by mapping workers to agent slots: each operator, regardless of whether it is backed by an RL policy, an LLM, or a human, conforms to a minimal universal interface. (iii) A deterministic cross-paradigm evaluation framework with two complementary modes: a manual mode that advances up to

N

operators in lock-step under shared seeds for fine-grained visual inspection of behavioural differences; and a script mode that drives automated, long-running evaluation via declarative Python scripts for reproducible experiments. Our documentation is released at: https://mosaic-platform.readthedocs.io.

Abdulhamid M. Mousa, Jinhui Pang, Rakhmonberdi Khajiev +5

School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China · School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China · Mathematics Department, Faculty of Science, Ain Shams University, Cairo, Egypt +1

AI Agent Evaluation Agent Evaluation Multi-Agent Collaboration Human-in-the-Loop AI