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.

May 7, 2026

From Surface Learning to Deep Understanding: A Grounded AI Tutoring System for Moodle

This demo paper describes the development of the AI Teaching & Learning Assistant, a modular Moodle plugin that leverages Retrieval-Augmented Generation (RAG) to deliver high-quality, hallucination-free education. The system employs a dual-centric design, providing students with interactive, Socratic-based tutoring and educators with a "human-in-the-loop" workspace for supervised content generation. By grounding Large Language Model (LLM) responses in teacher-provided materials, the assistant addresses the risks of misinformation while encouraging deep conceptual mastery. Evaluation via the Ragas (LLM-as-a-Judge) framework and a preliminary user study confirms its effectiveness, achieving faithfulness scores up to 0.97 and a 4.00/5.00 recommendation rate.

Anna Ostrowska, Michał Kukla, Gabriela Majstrak +4

Faculty of Mathematics and Information Sciences, Warsaw University of Technology, Warsaw, Poland

Intelligent Tutoring Systems AI in Education Generative AI in Education Socratic Tutoring Human-in-the-Loop AI

May 7, 2026

PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI

Recent developments in AI safety research have called for red-teaming methods that effectively surface potential risks posed by generative AI models, with growing emphasis on how red-teamers' backgrounds and perspectives shape their strategies and the risks they uncover. While automated red-teaming approaches promise to complement human red-teaming through larger-scale exploration, existing automated approaches do not account for human identities and rarely incorporate human inputs. In this work, we explore persona-driven red-teaming to advance both automated red-teaming and human-AI collaboration. We first develop PersonaTeaming Workflow, which incorporates personas into the adversarial prompt generation process to explore a wider spectrum of adversarial strategies. Compared to RainbowPlus, a state-of-the-art automated red-teaming method, PersonaTeaming Workflow achieves higher attack success rates while maintaining prompt diversity. However, since automated personas only approximate real human perspectives, we further instantiate PersonaTeaming Workflow as PersonaTeaming Playground, a user-facing interface that enables red-teamers to author their own personas and collaborate with AI to mutate and refine prompts. In a user study with 11 industry practitioners, we found that PersonaTeaming Playground enabled diverse red-teaming strategies and outputs that practitioners perceived as useful, and that AI-generated suggestions in the PersonaTeaming Playground encouraged out-of-the-box thinking even when practitioners did not follow them strictly. Together, our work advances both automated and human-in-the-loop approaches to red-teaming, while shedding light on interaction patterns and design insights for supporting human-AI collaboration in generative AI red-teaming.

Wesley Hanwen Deng, Mingxi Yan, Sunnie S. Y. Kim +5

Carnegie Mellon University Pittsburgh, Pennsylvania, USA · Apple Seattle, Washington, USA · Apple Cupertino, California, USA +1

Adversarial Prompt Generation LLM Red Teaming Human-in-the-Loop AI Automated Red Teaming Human-AI Collaboration

May 6, 2026

AICoFe: Implementation and Deployment of an AI-Based Collaborative Feedback System for Higher Education

Effective peer feedback is essential for developing critical reflection in higher education, yet its impact is often limited by the inconsistent quality of student-generated comments. This paper presents the implementation and deployment of AICoFe (AI-based Collaborative Feedback), a system designed to bridge this gap through a human-centered AI approach. We describe a modular architecture that orchestrates a multi-LLM pipeline, utilizing GPT-4.1-mini, Gemini 2.5 Flash, and Llama 3.1, to synthesize quantitative rubric data and qualitative observations into coherent, actionable feedback. Key to the system is a "teacher-in-the-loop" mediation workflow, where educators use specialized Learning Analytics dashboards to curate and refine AI-generated drafts before delivery. Furthermore, we detail the underlying data infrastructure, which employs a hybrid SQL and MongoDB strategy to ensure traceability and manage semi-structured feedback versions.

Alvaro Becerra, Alejandra Palma, Ruth Cobos

GHIA Group, School of Engineering, Universidad Autónoma de Madrid, Spain

Generative AI in Education Human-in-the-Loop AI

May 5, 2026

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, 2026

AIs and Humans with Agency

This paper compares agency in humans with potential agency in AI programs. Human agency takes many years to develop, as the frontal lobe is activated. Early attempts to endow LLMs agency have met serious obstacles. Progress requires a new architecture where actions and plans are formulated jointly with the human actors in each real world setting.

David Mumford

Human-in-the-Loop AI LLM Agents Human-AI Collaboration Agentic AI

May 4, 2026

U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning

LLMs are increasingly used for end-user task planning, yet their black-box nature limits users' ability to ensure reliability and control. While recent systems incorporate verification techniques, it remains unclear how users can effectively apply such rigid constraints to represent intent or adapt to real-world variability. For example, prior work finds that hard-only constraints are too rigid, and numeric flexibility weights confuse users. We investigate how interaction workflows can better support users in applying constraints to guide LLM-generated plans, examining whether abstracting strictness into high-level types (i.e., hard and soft) paired with distinct verification mechanisms helps users more reliably express and align intent. We present U-Define, a system that lets users define constraints in natural language and categorize them as either hard rules that must not be violated or soft preferences that allow flexibility. U-Define verifies these types through complementary methods: formal model checking for hard constraints and LLM-as-judge evaluation for soft ones. Through a technical evaluation and user studies with general and expert participants, we find that user-defined constraint types improve perceived usefulness, performance, and satisfaction while maintaining usability. These findings provide insights for designing flexible yet reliable constraint-based workflows.

Christine P Lee, Xinyu Jessica Wang, Aws Albarghouthi +2

University of Wisconsin–Madison, USA · George Mason University, USA

LLM Planning Human-in-the-Loop AI

May 3, 2026

Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective

This position paper argues that reliable AI requires infrastructure for human validation of implicit knowledge. AI learns from both explicit knowledge (papers, documentation, structured databases) and implicit knowledge (reasoning patterns, debugging processes, intermediate steps). Implicit knowledge remains unexternalized because documentation cost exceeds perceived value -- yet AI learns from it indiscriminately, acquiring both beneficial patterns and harmful biases. Current reliability methods can only verify explicit knowledge against sources, creating a fundamental gap: the most valuable AI capabilities (reasoning, judgment, intuition) are precisely those we cannot verify. We propose Knowledge Objects (KOs) -- structured artifacts that externalize implicit knowledge into forms humans can inspect, verify, and endorse. KOs transform verification economics: what was previously too costly to verify becomes feasible, enabling accumulated human validation to improve reliability over time.

Hengyu Liu, Tianyi Li, Zhihong Cui +5

Department of Computer Science, Aalborg University, Aalborg, Denmark · Department of Informatics, University of Oslo, Oslo, Norway · School of Computing, Macquarie University, Sydney, Australia

AI Agent Reliability Human-in-the-Loop AI Human-AI Collaboration

May 2, 2026

MILD: Mediator Agent System with Bidirectional Perception and Multi-Layered Alignment for Human-Vehicle Collaboration

Prior studies report that partial driving automation can increase the cognitive demands on human drivers. This effect largely arises from human drivers' lack of transparent insight into the vehicle's intentions and decision logic, as well as from automated systems' limited awareness of the driver's dynamic state and preferences. This bidirectional misalignment undermines shared situational awareness and exacerbates coordination failures in human-vehicle interaction. To address these limitations, we argue for a paradigm shift that elevates the human role from passive supervisor to active manager. We introduce the Mediator-in-the-Loop-Driving (MILD) system, based on an agentic system architecture to facilitate synergistic human-vehicle collaboration. MILD integrates a perception agent for joint in-cabin and out-of-cabin understanding with a lightweight strategy agent that generates compliant and explainable action suggestions. To ensure these strategies are strictly aligned with safety regulations and human values, we develop Evidence- and Constraint-weighted Policy Optimization (ECPO). ECPO leverages automatic validators to steer the agent toward behaviors that are not only accurate but also structurally complete, substantiated by evidence, and free from constraint violations. Furthermore, a retrieval-augmented generation module dynamically incorporates constraints from traffic regulations, speed recommendations, and driver preferences into the decision loop. Field experiments across three open datasets demonstrate that MILD consistently outperforms baselines in both perception accuracy and strategy quality under auditable offline metrics, and yields higher human-rated policy adequacy, comfort, and explanation than baselines. This work offers a practical pathway for building auditable and aligned agents for human-vehicle collaborative driving.

Jiyao Wang, Yunbiao Wang, Yubo Jiao +6

Department of Civil Engineering, McGill University, Montreal H3A 0G4, Quebec, Canada · Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, Guangdong, China · Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg L-4365, Luxembourg

AI Alignment AI Agent Safety Human-in-the-Loop AI Autonomous Driving Planning

May 1, 2026

Virtual Speech Therapist: A Clinician-in-the-Loop AI Agent for Speech Therapy Planning

This paper presents a proof of concept of the Virtual Speech Therapist (VST), an intelligent multi-agent based system designed to support stuttering assessment and individualized therapy planning through artificial intelligence (AI) driven workflows. VST integrates deep learning (DL) based stuttering detection fSD with large language model (LLM) based agentic system to assist clinicians in developing evidence informed therapy plans. The VST system begins with the acquisition and feature extraction of given speech samples, followed by the detection of stuttering types. Building on these speech driven information S, VST initiates an agentic reasoning process in which specialized LLM agents autonomously generate, critique, and iteratively refine individualized therapy plans P. A dedicated CriticAgent πca acts as a structured self-refinement mechanism, reviewing the generated therapy plans P and identifying areas for potential improvement in consistency, methodological soundness, and alignment with available evidence and professional guidelines. The resulting therapy plan P is presented then as a draft for clinician review. Clinician feedback can then be incorporated to produce a revised plan P, thereby maintaining a clinician-in-the-loop (CITL) paradigm. An initial evaluation, involving expert speech language pathologist (SLP) examines the clinical interpretability and feasibility of the generated therapy plans. Taken together, the results show the potential of VST to augment clinician-led therapy planning and provide a promising basis for future studies evaluating its integration into real world clinical settings. An interactive user interface for the proposed prototype is available online at: https://vocametrix.com/ai/stuttering-therapy-planning-agent, facilitating interactive stuttering assessment and stuttering therapy planning.

Shakeel Sheikh, Patrick Marmaroli, MD Sahidullah +4

The Kashmir Hub for Artficial Intelligence, The KHAIR, Basel, 4056, Switzerland. · Microsoft / Vocametrix, Tallinn, Estonia. · IAI, TCG CREST, West Bengal, India. +5

Speech Processing Human-in-the-Loop AI

May 1, 2026

Sketch-to-Layout: A Human-Centric Computational Agent for Constraint-Aware Synthesis of Modular Photobioreactors

Building-integrated photobioreactors (PBRs) offer a pathway for carbon-neutral architecture, yet deployment is hindered by configuration complexity and biological maintenance. This paper presents a modular PBR facade system powered by a computational framework reconciling design intent with physical validity. We introduce 'carbon-neutralization bricks' featuring integrated vessel-and-conduit geometry; monolithic fluid channels enable 'plug-and-play' assembly. To navigate the combinatorial complexity of 14 modular geometries, we develop a Computational Sketch-to-Layout Agent that formulates layout synthesis as a Constraint Satisfaction Problem (CSP). Using the CP-SAT engine, the agent treats sparse user sketches as soft priors while enforcing hard constraints like port alignment and global connectivity. This allows non-experts to synthesize fabrication-ready configurations in near real-time. Furthermore, to facilitate autonomous maintenance, we propose a weakly supervised algae health monitoring pipeline. By employing a hybrid CNN-attention backbone and a temporal ranking loss, the system quantifies biological vitality from photographs without absolute ground-truth labels. Experiments demonstrate the CSP solver achieves a 95.5% success rate on grid scales up to 15 x 15. Qualitative evaluations confirm the framework preserves design semantics while ensuring operational integrity. Long-term tests show the vision module produces health trajectories aligned with 14-day biological cycles, suggesting that integrating interactive synthesis with low-cost computer vision can democratize scalable carbon capture systems.

Xiujin Liu, Shuqi Li, Yuxin Lin

1Qrafty Technology Inc. · University of Michigan

Human-in-the-Loop AI

May 1, 2026

Skills as Verifiable Artifacts: A Trust Schema and a Biconditional Correctness Criterion for Human-in-the-Loop Agent Runtimes

Agent skills - structured packages of instructions, scripts, and references that augment a large language model (LLM) without modifying the model itself - have moved from convenience to first-class deployment artifact. The runtime that loads them inherits the same problem package managers and operating systems have always faced: a piece of content claims a behavior; the runtime must decide whether to believe it. We argue this paper's central thesis up front: a skill is untrusted code until it is verified, and the runtime that loads it must enforce that default rather than infer trust from a signature, a clearance, or a registry of origin. Without skill verification, a human-in-the-loop (HITL) gate must fire on every irreversible call - which is operationally untenable and degrades into rubber-stamping at any non-trivial scale. With skill verification treated as a separate, gated process, HITL fires only for what is unverified, and the system becomes sustainable. We give a trust schema that includes an explicit verification level on every skill manifest; a capability gate whose HITL policy is a function of that verification level; a biconditional correctness criterion that any candidate verification procedure must satisfy on an adversarial-ensemble exercise; and a portable runtime profile with ten normative guidelines abstracted from a working open-source reference implementation. The contribution is harness- and model-agnostic; nothing here requires retraining, fine-tuning, or proprietary infrastructure.

Alfredo Metere

Enclawed, LLC, California, USA

AI Agent Security LLM Agent Verification Human-in-the-Loop AI Capability-Based Security

May 1, 2026

Human-AI Coordination Zones: A Framework for Designing Human-in-the-Loop Experiences with Agentic AI

As generative and agentic AI becomes embedded in everyday products, practitioners face a persistent challenge: how to design human-AI coordination -- the ongoing mutual adjustment between users and AI systems as mediate through interfaces-that supports usability, trust, and safety. Existing resources offer high-level principles ("be transparent," "maintain user control") or low-level UI patterns, but there is a lack of mid-level design knowledge bridging the two. Through landscape and artifact analysis of 60 commercial AI applications, we introduce a framework defining human-AI coordination as the interplay of three dimensions: salience (how prominently AI is presented), involvement (what users can do to engage AI), and activity (what AI actually does). We contribute mid-level tools including coordination zones (done-for-me, done-under-me, done-with-me, done-without-me), an input taxonomy (prompted, sparked, inferred, layered), coordination curves for mapping user journeys, and design patterns demonstrating the generative capacity of the framework. The framework can be applied generatively to design experiences, analytically to evaluate existing ones, and communicatively to articulate ideas across stakeholders.

James Pierce, Vaiva Kalnikaitė, Siddharth Gupta +1

Amazon Web Services

Human-in-the-Loop AI Human-AI Interaction Human-AI Collaboration Agentic AI

Apr 30, 2026

Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications

Inertial Confinement Fusion (ICF) holds transformative promise for sustainable, near-limitless clean energy, yet remains constrained by prohibitively high costs and limited experimental opportunities. This paper presents Human-in-the-Loop Meta Bayesian Optimization (HL-MBO), a framework that integrates expert knowledge with few-shot, uncertainty-aware machine learning to accelerate discovery in data-scarce, high-stakes scientific domains. HL-MBO introduces a meta-learned surrogate model with an expert-informed acquisition function to recommend candidate experiments. To foster trust and enable informed decisions, HL-MBO also provides interpretable explanations of its suggestions. We show HL-MBO outperforms current BO methods on ICF energy yield optimization, as well as benchmarks in molecular optimization and critical temperature maximization for superconducting materials.

Ricardo Luna Gutierrez, Sahand Ghorbanpour, Ejaz Rahman +5

1Hewlett Packard Enterprise · University of Rochester

Meta-Learning Bayesian Optimization Human-in-the-Loop AI

Apr 27, 2026

TSAssistant: A Human-in-the-Loop Agentic Framework for Automated Target Safety Assessment

Target Safety Assessment (TSA) requires systematic integration of genetic, transcriptomic, target homology, pharmacological, and clinical data to evaluate potential safety liabilities of therapeutic targets. This process is labor-intensive and expert-dependent, posing challenges in scalability and reproducibility. We present TSAssistant, a human-in-the-loop multi-agent framework that decomposes TSA report generation into a workflow of specialized subagents: Research Subagents that each ground and cite a single TSA domain, and Synthesis Subagents that integrate findings across domains. Subagents retrieve and synthesize evidence from curated biomedical sources through standardized tool interfaces and produce individually citable, evidence-grounded sections, with behavior shaped by a hierarchical instruction architecture that separates coordination logic from domain expertise and user intent. To complement these soft constraints, programmatic execution hooks and persistent memory stores enforce hard constraints across the workflow, while an interactive refinement loop allows experts to review and revise individual sections with full conversational context preserved across iterations. Rather than a single holistic comparison, we decompose report quality into reproducibility, evidential grounding, task-level accuracy, and controllability under expert oversight, finding high reproducibility and grounding, substantial agreement with the human reference, and net-positive expert-driven refinement.

Xiaochen Zheng, Zhiwen Jiang, David Tokar +5

Predictive Modelling, Roche, Basel, Switzerland · Computational Sciences Center of Excellence, Roche, Basel, Switzerland · Translational Safety, Roche, Basel, Switzerland

LLM Agent Orchestration Human-in-the-Loop AI Scientific Workflow Automation

Apr 26, 2026

Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows

We present a deployed system that automates end-to-end customer support workflows inside an enterprise Business Process Management (BPM) platform. The approach is scalable in production and reaches selective automation within two weeks for a new process, leveraging supervision already generated at scale: structured per-case UI interaction traces and low-overhead copilot feedback, where operators either accept a suggestion or provide a correction. A staged deployment pipeline trains a next UI action policy, learns a critic from copilot feedback to calibrate abstention, and executes only high-confidence steps in the background while deferring uncertain decisions to operators and resuming from the updated UI state. This setup lets one operator supervise multiple concurrent sessions and be interrupted only when the system is uncertain. The system operates on a schema-driven view of the BPM interface and includes monitoring and safe fallbacks for production. In production, it automated 45% of sessions and reduced average handling time by 39% without degrading support quality level.

Nikita Borovkov, Elisei Rykov, Olga Tsymboi +4

T-Tech

Selective Prediction Customer Support Automation Business Process Automation Human-in-the-Loop AI GUI Automation

Apr 25, 2026

Revisable by Design: A Theory of Streaming LLM Agent Execution

Current LLM agents operate under an implicit but universal assumption: execution is a transaction -- the user submits a request, the agent works in isolation, and only upon completion does the dialogue resume. This forces users into a binary choice: wait for a potentially incorrect output, or interrupt and lose all progress. We reject this assumption and propose the stream paradigm, in which agent execution and user intervention are concurrent, interleaved processes sharing a bidirectional channel. We formalize this paradigm through a reversibility taxonomy that classifies every agent action as Idempotent, Reversible, Compensable, or Irreversible, and arrive at a core conclusion: an agent's flexibility is bounded by its reversibility. We prove that conflicting compensable actions impose unavoidable adaptation costs and that conflicting irreversible actions make full specification satisfaction impossible -- these costs are properties of the action space, not of the algorithm. Guided by this insight, we present the Revision Absorber, a reactive algorithm based on the Earliest-Conflict Rollback rule that is structurally optimal under mild assumptions. Experiments on StreamBench with real LLM agents validate all predictions: the Absorber matches the quality of a brute-force full-restart baseline while wasting an order of magnitude fewer steps of already-completed work, turning mid-execution revisions from a dead-end into a first-class interaction.

Zhiyuan Zhai, Ming Li, Xin Wang

Fudan University · Guangming Lab

Human-in-the-Loop AI LLM Agents

Apr 25, 2026

AI-Assisted Code Review as a Scaffold for Code Quality and Self-Regulated Learning: An Experience Report

Code review is central to software engineering education but hard to scale in capstone projects due to tight deadlines, uneven peer feedback, and limited prior experience. We investigate an LLM-as-reviewer integrated directly into GitHub pull requests (human-in-the-loop) across two cohorts (more than 100 students, 2023--2024). Using a mixed-methods design -- GitHub data, reflective reports, and a targeted survey -- we examine engagement and responsiveness as behavioral indicators of self-regulated learning processes. Quantitatively, the 2024 cohort produced more iterative activity (1176 vs. 581 PRs), while technical issues observed in 2023 (227 failed AI attempts) dropped to zero after tool and instructional refinements. Despite different adoption levels (93% vs. 50% of teams using the tool), responsiveness was stable: 32% (2023) and 33% (2024) of successfully AI-reviewed PRs were followed by subsequent commits on the same PR. Qualitatively, students used the LLM's structured comments to focus reviews and discuss code quality, while guidance reduced over-reliance. We contribute: (i) an in-workflow design for an AI reviewer that scaffolds learning while mitigating cognitive offloading; (ii) a repeated cross sectional comparison across two cohorts in authentic settings; (iii) a mixed-methods analysis combining objective GitHub metrics with student self-reports; and (iv) evidence-based pedagogical recommendations for responsible, student-led AI-assisted review.

Eduardo Oliveira, Michael Fu, Patanamon Thongtanunam +2

The University of Melbourne Melbourne, Australia · University of Eastern Finland Joensuu, Finland

Self-Regulated Learning Generative AI in Education Human-in-the-Loop AI Automated Code Review AI-Assisted Software Development

Apr 24, 2026

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 24, 2026

FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean

Formalising informal mathematical reasoning into formally verifiable code is a significant challenge for large language models. In scientific fields such as physics, domain-specific machinery (e.g. Dirac notation, vector calculus) imposes additional formalisation challenges that modern LLMs and agentic approaches have yet to tackle. To aid autoformalisation in scientific domains, we present FormalScience; a domain-agnostic human-in-the-loop agentic pipeline that enables a single domain expert (without deep formal language experience) to produce syntactically correct and semantically aligned formal proofs of informal reasoning for low economic cost. Applying FormalScience to physics, we construct FormalPhysics, a dataset of 200 university-level (LaTeX) physics problems and solutions (primarily quantum mechanics and electromagnetism), along with their Lean4 formal representations. Compared to existing formal math benchmarks, FormalPhysics achieves perfect formal validity and exhibits greater statement complexity. We evaluate open-source models and proprietary systems on a statement autoformalisation task on our dataset via zero-shot prompting, self-refinement with error feedback, and a novel multi-stage agentic approach, and explore autoformalisation limitations in modern LLM-based approaches. We provide the first systematic characterisation of semantic drift in physics autoformalisation in terms of concepts such as notational collapse and abstraction elevation which reveals what formal language verifies when full semantic preservation is unattainable. We release the codebase together with an interactive UI-based FormalScience system which facilitates autoformalisation and theorem proving in scientific domains beyond physics.https://github.com/jmeadows17/formal-science

Jordan Meadows, Lan Zhang, Andre Freitas

Independent Researcher · University of Manchester, UK · Idiap Research Institute, Switzerland +1

Human-in-the-Loop AI Agentic Code Generation Autoformalization

Apr 23, 2026

Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training

Post-training is essential for turning pretrained generalist robot policies into reliable task-specific controllers, but existing human-in-the-loop pipelines remain tied to physical execution: each correction requires robot time, scene setup, resets, and operator supervision in the real world. Meanwhile, action-conditioned world models have been studied mainly for imagination, synthetic data generation, and policy evaluation. We propose Human-in-the-World-Model (Hi-WM), a post-training framework that uses a learned world model as a reusable corrective substrate for failure-targeted policy improvement. A policy is first rolled out in closed loop inside the world model; when the rollout becomes incorrect or failure-prone, a human intervenes directly in the model to provide short corrective actions. Hi-WM caches intermediate states and supports rollback and branching, allowing a single failure state to be reused for multiple corrective continuations and yielding dense supervision around behaviors that the base policy handles poorly. The resulting corrective trajectories are then added back to the training set for post-training. We evaluate Hi-WM on three real-world manipulation tasks spanning both rigid and deformable object interaction, and on two policy backbones. Hi-WM improves real-world success by 37.9 points on average over the base policy and by 19.0 points over a world-model closed-loop baseline, while world-model evaluation correlates strongly with real-world performance (r = 0.953). These results suggest that world models can serve not only as generators or evaluators, but also as effective corrective substrates for scalable robot post-training.

Yaxuan Li, Zhongyi Zhou, Yefei Chen +5

Current Robotics · Tsinghua University · Peking University +1

Robot Policy Learning Robot Policy Adaptation Robot Skill Learning World Models for Robotics Action-Conditioned World Models Human-in-the-Loop AI+1

Apr 22, 2026

Mind the Prompt: Self-adaptive Generation of Task Plan Explanations via LLMs

Integrating Large Language Models (LLMs) into complex software systems enables the generation of human-understandable explanations of opaque AI processes, such as automated task planning. However, the quality and reliability of these explanations heavily depend on effective prompt engineering. The lack of a systematic understanding of how diverse stakeholder groups formulate and refine prompts hinders the development of tools that can automate this process. We introduce COMPASS (COgnitive Modelling for Prompt Automated SynthesiS), a proof-of-concept self-adaptive approach that formalises prompt engineering as a cognitive and probabilistic decision-making process. COMPASS models unobservable users' latent cognitive states, such as attention and comprehension, uncertainty, and observable interaction cues as a POMDP, whose synthesised policy enables adaptive generation of explanations and prompt refinements. We evaluate COMPASS using two diverse cyber-physical system case studies to assess the adaptive explanation generation and their qualities, both quantitatively and qualitatively. Our results demonstrate the feasibility of COMPASS integrating human cognition and user profile's feedback into automated prompt synthesis in complex task planning systems.

Gricel Vázquez, Alexandros Evangelidis, Sepeedeh Shahbeigi +2

University of York, UK · Cyprus University of Technology, Cyprus

Explainable Artificial Intelligence Human-in-the-Loop AI Prompt Engineering

Apr 22, 2026

pAI/MSc: ML Theory Research with Humans on the Loop

We present pAI/MSc, an open-source, customizable, modular multi-agent system for academic research workflows. Our goal is not autonomous scientific ideation, nor fully automated research. It is narrower and more practical: to reduce by orders of magnitude the human steering required to turn a specified hypothesis into a literature-grounded, mathematically established, experimentally supported, submission-oriented manuscript draft. pAI/MSc is built with a current emphasis on machine learning theory and adjacent quantitative fields.

Mahmoud Abdelmoneum, Pierfrancesco Beneventano, Tomaso Poggio

1Massachusetts Institute of Technology · 2Perseus Labs

Multi-Agent LLM Systems AI-Assisted Scientific Research Human-in-the-Loop AI

Apr 22, 2026

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, 2026

From Fuzzy to Formal: Scaling Hospital Quality Improvement with AI

Hospital Quality Improvement (QI) plays a critical role in optimizing healthcare delivery by translating high-level hospital goals into actionable solutions. A critical step of QI is to identify the key modifiable contributing factors, a process we call QI factor discovery, typically through expert-driven semi-structured qualitative tools like fishbone diagrams, chart reviews, and Lean Healthcare methods. AI has the potential to transform and accelerate QI factor discovery, which is traditionally time- and resource-intensive and limited in reproducibility and auditability. Nevertheless, current AI alignment methods assume the task is well-defined, whereas QI factor discovery is an exploratory, fuzzy, and iterative sense-making process that relies on complex implicit expert judgments. To design an AI pipeline that formalizes the QI process while preserving its exploratory components, we propose viewing the task as learning not only LLM prompts but also the overarching natural-language specifications. In particular, we map QI factor discovery to steps of the classical AI/ML development process (problem formalization, model learning, and model validation) where the specifications are tunable hyperparameters. Domain experts and AI agents iteratively refine both the overarching specifications and AI pipeline until AI extractions are concordant with expert annotations and aligned with clinical objectives. We applied this "Human-AI Spec-Solution Co-optimization" framework at an urban safety-net hospital to identify factors driving prolonged length of stay and unplanned 30-day readmissions. The resulting AI-for-QI pipelines achieved

\ge 70\%

concordance with expert annotations. Compared to prior manual Lean analyses, the AI pipeline was substantially more efficient, recovered previous findings, surfaced new modifiable factors, and produced auditable reasoning traces.

Patrick Vossler, Jean Feng, Venkat Sivaraman +9

University of California, San Francisco · 2Zuckerberg San Francisco General Hospital

Human-in-the-Loop AI Automatic Prompt Optimization

Apr 21, 2026

BONSAI: A Mixed-Initiative Workspace for Human-AI Co-Development of Visual Analytics Applications

Developing Visual Analytics (VA) applications requires integrating complex machine learning models with expressive interactive interfaces. Developers face a stark trade-off: building tightly-coupled monoliths plagued by fragile interdependencies, or relying on restrictive, simplistic frameworks. Meanwhile, unconstrained, single-shot AI code generation promises speed but yields unstructured, unauditable chaos. The core challenge is combining the control and expressiveness of custom development with the efficiency of AI generation under strict constraints. To address this, we introduce BONSAI, a mixed-initiative workspace for the multi-agent co-development of VA applications. BONSAI utilizes a modular four-layer architecture (hardware, services, orchestration, application) that allows human and AI developers to independently contribute reusable components. The workspace incorporates this architecture into a structured four-phase development process (plan, design, monitor, and review), ensuring distributed agency and full provenance, where all human and AI contributions are structurally bounded and tracked. We evaluate BONSAI through case studies demonstrating the efficient creation of novel tools and the rapid reconstruction of complex VA applications directly from research paper descriptions. Ultimately, this paper contributes a conceptual workflow, a scalable architecture, and an integrated system that successfully balances AI's generative speed with the structural rigor required for complex VA development.

Thilo Spinner, Matthias Miller, Fabian Sperrle-Roth +1

Thilo Spinner · Matthias Miller · Fabian Sperrle-Roth +1

Multi-Agent Collaboration Human-in-the-Loop AI Visual Analytics Human-AI Co-Creation AI-Assisted Software Development

Apr 19, 2026

CoAct: Co-Active LLM Preference Learning with Human-AI Synergy

Learning from preference-based feedback has become an effective approach for aligning LLMs across diverse tasks. However, high-quality human-annotated preference data remains expensive and scarce. Existing methods address this challenge through either self-rewarding, which scales by using purely AI-generated labels but risks unreliability, or active learning, which ensures quality through oracle annotation but cannot fully leverage unlabeled data. In this paper, we present CoAct, a novel framework that synergistically combines self-rewarding and active learning through strategic human-AI collaboration. CoAct leverages self-consistency to identify both reliable self-labeled data and samples that require oracle verification. Additionally, oracle feedback guides the model to generate new instructions within its solvable capability. Evaluated on three reasoning benchmarks across two model families, CoAct achieves average improvements of +13.25% on GSM8K, +8.19% on MATH, and +13.16% on WebInstruct, consistently outperforming all baselines.

Ruiyao Xu, Mihir Parmar, Tiankai Yang +3

Northwestern University · Google · University of Southern California +1

RL for Language Models LLM Alignment Active Learning Human-in-the-Loop AI

Apr 16, 2026

An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data

Wearable devices generate continuous physiological and behavioral data, but converting these signals into clinically reviewable biomarker hypotheses remains labor-intensive. We introduce CoDaS, an AI co-data-scientist that integrates multi-agent hypothesis generation, deterministic statistical analysis, adversarial validation and literature-grounded interpretation under human oversight. Across three wearable cohorts comprising 9,279 participant-observations, CoDaS prioritized candidate associations for mental-health and metabolic endpoints after internal checks for replication, stability, robustness and leakage. The system identified related circadian-instability signals associated with depression, including sleep-duration variability in DWB (

ρ

= 0.252,

p

< 0.001) and sleep-onset variability in GLOBEM (

ρ

= 0.126,

p

< 0.001), and derived a wearable cardiovascular-fitness index associated with insulin resistance (steps/resting heart rate;

ρ

= -0.374,

p

< 0.001). Adding these features to demographic models produced modest gains (

ΔR^2

= 0.040 for depression, 0.021 for insulin resistance). In a 12-clinician review totaling approximately 25 active hours, clinician validity judgments aligned with CoDaS confidence tiers (

ρ

= 0.67,

p

= 0.005), whereas added clinical value and confidence to act were rated lower. CoDaS supports traceable, hypothesis-generating prioritization of wearable candidate biomarkers.

Yubin Kim, Salman Rahman, Samuel Schmidgall +33

Google Research · Massachusetts Institute of Technology · Google DeepMind +7

AI Agents for Scientific Discovery Scientific Discovery Human-in-the-Loop AI Wearable Health Monitoring

Apr 16, 2026

GDPR Auto-Formalization with AI Agents and Human Verification

We study the overall process of automatic formalization of GDPR provisions using large language models, within a human-in-the-loop verification framework. Rather than aiming for full autonomy, we adopt a role-specialized workflow in which LLM-based AI components, operating in a multi-agent setting with iterative feedback, generate legal scenarios, formal rules, and atomic facts. This is coupled with independent verification modules which include human reviewers' assessment of representational, logical, and legal correctness. Using this approach, we construct a high-quality dataset to be used for GDPR auto-formalization, and analyze both successful and problematic cases. Our results show that structured verification and targeted human oversight are essential for reliable legal formalization, especially in the presence of legal nuance and context-sensitive reasoning.

Ha Thanh Nguyen, Wachara Fungwacharakorn, Sabine Wehnert +6

Center for Juris-Informatics, ROIS-DS Tokyo, Japan · Ruhr-University Bochum, RC-Trust Bochum, Germany · Uniwersytet Jagielloński w Krakowie Kraków, Poland +1

Human-in-the-Loop AI

Apr 13, 2026

Agentic Driving Coach: Robustness and Determinism of Agentic AI-Powered Human-in-the-Loop Cyber-Physical Systems

Foundation models, including large language models (LLMs), are increasingly used for human-in-the-loop (HITL) cyber-physical systems (CPS) because foundation model-based AI agents can potentially interact with both the physical environments and human users. However, the unpredictable behavior of human users and AI agents, in addition to the dynamically changing physical environments, leads to uncontrollable nondeterminism. To address this urgent challenge of enabling agentic AI-powered HITL CPS, we propose a reactor-model-of-computation (MoC)-based approach, realized by the open-source Lingua Franca (LF) framework. We also carry out a concrete case study using the agentic driving coach as an application of HITL CPS. By evaluating the LF-based agentic HITL CPS, we identify practical challenges in reintroducing determinism into such agentic HITL CPS and present pathways to address them.

Deeksha Prahlad, Daniel Fan, Hokeun Kim

Arizona State University Tempe, AZ, United States

Human-in-the-Loop AI Cyber-Physical Systems AI Agent Reliability

Apr 13, 2026

Toward Human-AI Complementarity Across Diverse Tasks

Human-AI complementarity, the idea that combining human and AI judgments can outperform either alone, offers a promising pathway toward robust oversight of advanced AI systems. However, whether human-AI complementarity can be achieved on realistic tasks remains an open question. We investigate this through two approaches: hybridization and two AI assistance methods (top-2 assistance and subtask delegation), evaluated on a multi-domain dataset of 1,886 samples spanning knowledge, factuality, long-context reasoning, and deception detection. We find only modest complementarity gains. Baseline hybridization yields just +0.4 percentage points (pp) over AI alone (69.3% vs 68.9%), limited both by a small complementarity region (only 8.9% of items where AI errs but humans do not) and the inability of confidence-based routing to identify it, since the model's confidence is similarly distributed across correct and incorrect predictions. Applied when AI has low confidence, top-2 assistance increases human accuracy from 28.4% to 38.3%, surpassing AI alone (37.7%) -- but primarily because humans adopt correct AI suggestions, not because they successfully override AI errors. These findings suggest that the primary bottleneck is not human task accuracy per se, but the ability to route decisions to humans when it matters and to design assistance methods that enable humans to catch AI mistakes. Our quantitative and qualitative analyses pinpoint where and why each method succeeds or fails, offering concrete targets for future work. We will release our dataset and code upon request to support progress toward more effective human-AI collaboration for AI oversight.

Yuzheng Xu, Annya Dahmani, Matthew D. Blanchard +13

The University of Tokyo · UC Berkeley · University of Sydney +6

Human-AI Complementarity Human-AI Decision Making Human-AI Collaboration Human-in-the-Loop AI Human Oversight of AI