Overview

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

312 papers30 papers in the last four weeks, down 6% on the four weeks before. 0.2% of all new papers.

Feb 18, 2026

AI-Mediated Feedback Improves Student Revisions: A Randomized Trial with FeedbackWriter in a Large Undergraduate Course

Despite growing interest in using LLMs to generate feedback on students' writing, little is known about how students respond to AI-mediated versus human-provided feedback. We address this gap through a randomized controlled trial in a large introductory economics course (N=354), where we introduce and deploy FeedbackWriter - a system that generates AI suggestions to teaching assistants (TAs) while they provide feedback on students' knowledge-intensive essays. TAs have the full capacity to adopt, edit, or dismiss the suggestions. Students were randomly assigned to receive either handwritten feedback from TAs (baseline) or AI-mediated feedback where TAs received suggestions from FeedbackWriter. Students revise their drafts based on the feedback, which is further graded. In total, 1,366 essays were graded using the system. We found that students receiving AI-mediated feedback produced significantly higher-quality revisions, with gains increasing as TAs adopted more AI suggestions. TAs found the AI suggestions useful for spotting gaps and clarifying rubrics.
Feb 18, 2026

Measuring Mid-2025 LLM-Assistance on Novice Performance in Biology

Large language models (LLMs) perform strongly on biological benchmarks, raising concerns that they may help novice actors acquire dual-use laboratory skills. Yet, whether this translates to improved human performance in the physical laboratory remains unclear. To address this, we conducted a pre-registered, investigator-blinded, randomized controlled trial (June-August 2025; n = 153) evaluating whether LLMs improve novice performance in tasks that collectively model a viral reverse genetics workflow. We observed no significant difference in the primary endpoint of workflow completion (5.2% LLM vs. 6.6% Internet; P = 0.759), nor in the success rate of individual tasks. However, the LLM arm had numerically higher success rates in four of the five tasks, most notably for the cell culture task (68.8% LLM vs. 55.3% Internet; P = 0.059). Post-hoc Bayesian modeling of pooled data estimates an approximate 1.4-fold increase (95% CrI 0.74-2.62) in success for a "typical" reverse genetics task under LLM assistance. Ordinal regression modelling suggests that participants in the LLM arm were more likely to progress through intermediate steps across all tasks (posterior probability of a positive effect: 81%-96%). Overall, mid-2025 LLMs did not substantially increase novice completion of complex laboratory procedures but were associated with a modest performance benefit. These results reveal a gap between in silico benchmarks and real-world utility, underscoring the need for physical-world validation of AI biosecurity assessments as model capabilities and user proficiency evolve.
Feb 17, 2026

Latency-aware Human-in-the-Loop Reinforcement Learning for Semantic Communications

Semantic communication promises task-aligned transmission but must reconcile semantic fidelity with stringent latency guarantees in immersive and safety-critical services. This paper introduces a time-constrained human-in-the-loop reinforcement learning (TC-HITL-RL) framework that embeds human feedback, semantic utility, and latency control within a semantic-aware Open radio access network (RAN) architecture. We formulate semantic adaptation driven by human feedback as a constrained Markov decision process (CMDP) whose state captures semantic quality, human preferences, queue slack, and channel dynamics, and solve it via a primal--dual proximal policy optimization algorithm with action shielding and latency-aware reward shaping. The resulting policy preserves PPO-level semantic rewards while tightening the variability of both air-interface and near-real-time RAN intelligent controller processing budgets. Simulations over point-to-multipoint links with heterogeneous deadlines show that TC-HITL-RL consistently meets per-user timing constraints, outperforms baseline schedulers in reward, and stabilizes resource consumption, providing a practical blueprint for latency-aware semantic adaptation.
Feb 17, 2026

RUVA: Personalized Transparent On-Device Graph Reasoning

The Personal AI landscape is currently dominated by "Black Box" Retrieval-Augmented Generation. While standard vector databases offer statistical matching, they suffer from a fundamental lack of accountability: when an AI hallucinates or retrieves sensitive data, the user cannot inspect the cause nor correct the error. Worse, "deleting" a concept from a vector space is mathematically imprecise, leaving behind probabilistic "ghosts" that violate true privacy. We propose Ruva, the first "Glass Box" architecture designed for Human-in-the-Loop Memory Curation. Ruva grounds Personal AI in a Personal Knowledge Graph, enabling users to inspect what the AI knows and to perform precise redaction of specific facts. By shifting the paradigm from Vector Matching to Graph Reasoning, Ruva ensures the "Right to be Forgotten." Users are the editors of their own lives; Ruva hands them the pen. The project and the demo video are available at http://sisinf00.poliba.it/ruva/.
Feb 2, 2026

Should There be a Teacher In-the-Loop? A Study of Generative AI-Personalized Tasks Middle School

Large language models can be used to design instructional tasks to align to students needs. These generative AI models can create tasks that correspond to students out-of-school interests in areas like sports or music, which may enhance students interest in learning. However, little is known about teachers processes for creating or modifying tasks with generative AI, despite commercial AI companies claims that they will save teachers time. In the present study, 7 middle school mathematics teachers used ChatGPT to create personalized versions of problems in their curriculum to correspond to their students interests. The prompting moves teachers made and their students open-ended feedback on personalized problems were examined through thematic analysis. Teachers efficiency when creating problems and the ratings of their 7th grade students who received personalized assignments were examined. Results from this sample suggest that having a teacher-in-the-loop may result in generative AI-enhanced personalization being enacted at a broad grain size, whereas students often expressed preference for a smaller grain-size where they receive specific popular culture references that interest them. Teachers used prompting to adjust popular culture references and address issues with the depth, ethics, or realism of the problems generated, in some cases showing epistemic agency. The article closes with an exploratory, design-focused look at scalability trade-offs with teacher-facing personalization, patterns of teacher prompting practices, and opportunities for teachers to exercise epistemic and ethical monitoring of personalization outputs.
Dec 1, 2025

First, do NOHARM: a medical safety benchmark and randomized study of physician and AI teaming on clinical consultations

Large language models (LLMs) and medical AI tools are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain poorly characterized. We present NOHARM (Numerous Options Harm Assessment for Risk in Medicine), a 1,100-task benchmark of primary care-to-specialist consultation cases to measure the frequency and severity of potentially harmful errors from LLM-generated medical consultation recommendations. NOHARM covers 10 specialties, with 12,747 expert annotations for 4,249 clinical management options. Across 20 notable LLMs and 4 widely used retrieval-augmented generation (RAG) clinical AI tools, direct application of recommendations carried potential for severe harm in up to 24.6% of cases, with errors of omission accounting for more than 80% of severe errors. Harm potential was not uniform across systems, with clinical AI tools outperforming generalist LLMs, and multi-agent AI teaming further improving performance in generalist models. In a randomized study of 101 U.S.-licensed generalist physicians, AI assistance improved physician performance compared to conventional resources. However, AI-assisted physicians frequently omitted valuable AI-generated recommendations and still scored lower than many AI systems alone. Had those recommendations been incorporated, combined human-AI responses would have outperformed both the human and AI system as used, suggesting complementary strengths and unrealized potential in human-AI teaming. Collectively, these results show that despite strong performance on medical knowledge benchmarks, widely used AI tools can produce medical consultation advice with the potential for severe harm, and highlight the need for explicit measurement of clinical safety. The benchmark and leaderboard are publicly available to support ongoing evaluation and improvement of AI systems used for clinical care.
Nov 4, 2025

A Collaborative Reasoning Framework for Anomaly Diagnostics in Underwater Robotics

The safe deployment of autonomous systems in safety-critical settings requires a paradigm that combines human expertise with AI-driven analysis, especially when anomalies are unforeseen. We introduce AURA (Autonomous Resilience Agent), a collaborative framework for anomaly and fault diagnostics in robotics. AURA integrates large language models (LLMs), a high-fidelity digital twin (DT), and human-in-the-loop interaction to detect and respond to anomalous behavior in real time. The architecture uses two agents with clear roles: (i) a low-level State Anomaly Characterization Agent that monitors telemetry and converts signals into a structured natural-language problem description, and (ii) a high-level Diagnostic Reasoning Agent that conducts a knowledge-grounded dialogue with an operator to identify root causes, drawing on external sources. Human-validated diagnoses are then converted into new training examples that refine the low-level perceptual model. This feedback loop progressively distills expert knowledge into the AI, transforming it from a static tool into an adaptive partner. We describe the framework's operating principles and provide a concrete implementation, establishing a pattern for trustworthy, continually improving human-robot teams.
Sep 23, 2025

Robotic Ultra-Long-Horizon Manipulation Skills via Human-guided Lifelong Code Generation

Large language models (LLMs) can translate natural-language instructions for robotic manipulation into executable code, but ambiguity, noisy generations, and limited context windows make ultra-long-horizon tasks unreliable. Closed-loop approaches that rely only on LLM feedback also struggle because LLMs have limited robotic reasoning, even when task errors are obvious to humans. Feedback is often stored in representations that generalize poorly to unseen tasks and can cause catastrophic forgetting as new corrections accumulate. We propose LYRA, a human-guided lifelong skill learning and code generation framework that distills human feedback into modular, reusable skills and incrementally extends their functionality across successive interactions while preserving previously learned behavior. External memory stores learned skills and execution examples; retrieval-augmented generation selects relevant knowledge, while user hints guide reuse when retrieval is insufficient, supporting ultra-long-horizon execution. Experiments on Ravens, Franka Kitchen, LIBERO-long, MetaWorld, and real-world tasks show a 0.93 success rate, up to 27% higher than baselines, and a 42% improvement in correction efficiency. LYRA also robustly solves ``build a house'', which requires planning over 20 primitives.
Sep 1, 2025

Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning

Large language models (LLMs) show strong reasoning via chain-of-thought (CoT) prompting, but the process is opaque, which makes verification, debugging, and control difficult in high-stakes settings. We present Vis-CoT, a human-in-the-loop framework that converts linear CoT text into an interactive reasoning graph. Users can visualize the logical flow, identify flawed steps, and intervene by pruning incorrect paths and grafting new, user-defined premises. This shifts interaction from passive observation to active collaboration, steering models toward more accurate and trustworthy conclusions. Across GSM8K and StrategyQA, Vis-CoT improves final-answer accuracy by up to 24 percentage points over non-interactive baselines. A user study also shows large gains in perceived usability and trust. Vis-CoT points to a practical path for more reliable, understandable, and collaborative reasoning by combining LLMs with targeted human oversight.
Aug 31, 2025

Ultra Strong Machine Learning: LLM-Generated Explanations Do Not Yet Suffice for Teaching Humans Active Learning Strategy

Active learning is a general learning mechanism shared by artificial and human learners. Whether AI can teach humans such a strategy that transfers across domains is an open question. Ultra Strong Machine Learning (USML), a system whose explanations quantifiably improve human out-of-sample performance compared to self-learning, is uniquely positioned to answer this question. Prior USML work relied on hand-crafted explanation templates that require expert effort for each new domain and do not scale. We developed an explanation pipeline combining Inductive Logic Programming (ILP) with large language models (LLMs) to automate explanation generation and scoring. We tested whether these explanations achieve USML in a human trial teaching active learning strategies across three related domains. Our exploratory results show that concise, expert-written explanations benefit learners with higher initial performance, while pipeline-generated explanations provide no advantage over self-learning despite being rated as higher quality from an LLM-as-judge evaluation. This case study reveals a systematic gap that LLM quality metrics do not predict human learning outcomes. Our findings point to explanation complexity relative to task difficulty as a key factor, and call for explanation methods and evaluation criteria grounded in human cognitive constraints rather than LLM preference.
Oct 1, 2024

iTeach: In the Wild Interactive Teaching for Failure-Driven Adaptation of Robot Perception

We present iTeach, a deployable system that lets any co-located human fix a robot's perception failures on the spot without expertise, a workstation, or offline retraining. The operator wears a mixed reality (MR) headset, sees the robot's segmentation predictions overlaid on the real scene, and corrects failures hands-free: rearranging objects (HumanPlay), annotating via gaze and voice, and triggering SAM2 backward mask propagation. Each ~20 s interaction yields 150-300 densely labeled training frames; the system fine-tunes the perception model onboard, keeps the better model, and redeploys, all without leaving the deployment site. The full loop requires only an RGB-D camera, onboard GPU, and an MR headset: any mobile robot, any environment. Starting from 26.1 on cluttered real-world scenes, 45 teaching interactions (13K frames) raise segmentation to 80.7 with no catastrophic forgetting; on three standard benchmarks the model never trained on, performance improves as well. Downstream pick-and-place on SceneReplica reaches 72/100, surpassing a model-based pipeline requiring CAD models. A 12-participant user study confirms non-experts match experts on annotation accuracy (~95% box IoU), speed, and task load (NASA-TLX 21/100). The framework is architecture-agnostic: any fine-tunable perception model can serve as backbone.
Aug 22, 2024

Human-In-The-Loop Machine Learning for Safe and Ethical Autonomous Vehicles: Principles, Challenges, and Opportunities

Machine Learning (ML) has become central to Autonomous Vehicles (AVs), supporting perception, prediction, planning, control, and decision-making in dynamic environments. However, achieving full autonomy in cluttered and complex scenarios, such as intricate intersections, diverse scenes, varied trajectories, and complex missions, remains challenging; moreover, data labeling is still a major bottleneck. These limitations motivate Human-in-the-Loop Machine Learning (HITL-ML), in which human input is incorporated through validation, annotation, task organization, reward design, action correction, preference feedback, and supervisory intervention. To advance safe and ethical autonomy, this paper presents a tutorial survey of HITL-ML for AVs, focusing on Curriculum Learning (CL), Human-in-the-Loop Reinforcement Learning (HITL-RL), Human-in-the-Loop Large Language Models (HITL-LLMs), Active Learning (AL), and ethical principles. We first review CL methods that structure training from simple to complex tasks, covering navigation, path planning, obstacle avoidance, data collection, landing, intersection handling, motion planning, and UAV swarm coordination. We then examine HITL-RL through reward shaping, action injection, demonstrations, preference-based feedback, and interactive learning, emphasizing improved learning efficiency, safer policy exploration, and real-time intervention. Next, we review HITL-LLM through collaboration and oversight and specify key challenges. After that, we discuss AL for perception, anomaly detection, semantic mapping, object detection, vehicle recognition, and security-related classification. Ethical principles are reviewed as technical requirements for transparency, accountability, human oversight, safety, security, regulatory compliance, and reliability of human input.