Latest Active Learning Research Papers

The newest Active Learning papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Active Learning so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Robust Bayesian Decision Making under Adversarial Uncertainty
  Haripriya Harikumar, Sammie Katt, Yasir Zubayr Barlas, Samuel Kaski · arXiv · Jul 9, 2026

  Scientific experiments are often designed to maximize information gain, yet in many applications the primary objective is to support reliable downstream decision-making. Existing decision-aware experimental design and active learning method…

• TriA Pipeline: A Large-Scale Automatic Audio Annotation Pipeline For Audio Classification In Specific Scenarios
  Hong Lyu, Mingru Yang, Qianhua He, Yanxiong Li et al. · arXiv · Jul 7, 2026

  There are some datasets of varying scales for audio classification (AC) applied to different tasks. However, annotated data is limited for most scenarios, such as domestic environments. To address this challenge, we propose an $\textbf{A}$u…

• Hedgementation = Hedgerow Segmentation: A Remote Sensing Benchmark
  Nathan Senyard, Salem Hamdani, Astrid Zhang, Derek Wang et al. · arXiv · Jun 22, 2026

  We propose Hedgementation: a new benchmark to evaluate machine learning models for hedgerow mapping from remote sensing data at country scale and 10m$^2$ spatial resolution. We combine and harmonize multiple remote sensing data products and…

• Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers
  Tianyi Li, Zhiqiang Shen · arXiv · Jun 22, 2026

  Linear mode connectivity (LMC) provides a promising foundation for understanding and merging independently trained neural networks, but existing methods typically optimize the interpolation path from only one model endpoint, limiting their …

• A Complexity Measure for Active Learning in Multi-group Mean Estimation
  Abdellah Aznag, Rachel Cummings, Adam N. Elmachtoub · arXiv · Jun 12, 2026

  We study a \emph{max-risk} objective for active learning in a multi-group mean estimation $d$-armed bandits: a learner adaptively allocates a budget of $T$ samples across $d$ groups to minimize the worst-case uncertainty index $\max_{k\in[d…

• ATLAS: Active Theory Learning for Automated Science
  Noémi Éltető, Nathaniel D. Daw, Kimberly L. Stachenfeld, Kevin J. Miller · arXiv · Jun 10, 2026

  Advancing scientific understanding through mechanistic modeling requires posing the right experimental questions to yield maximally informative data. To automate this pursuit within cognitive science, we introduce ATLAS (Active Theory Learn…

• Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
  Mengyu Zheng, Kai Han, Boxun Li, Haiyang Xu et al. · arXiv · Jun 10, 2026

  General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and pred…

• OncoTraj: a public benchmark for longitudinal resistance prediction in EGFR-mutant non-small-cell lung cancer on osimertinib
  Abhijoy Sarkar, Aarchi Singh Thakur · arXiv · Jun 9, 2026

  Resistance to first-line osimertinib in EGFR-mutant non-small-cell lung cancer (NSCLC) is the canonical example of predictable clonal evolution under therapeutic pressure, yet no public benchmark exists for training or evaluating computatio…

• Loss-Based Active Learning for Neural Abstractive Summarization
  Michail Ioannou, Tatiana Passali, Grigorios Tsoumakas · Greeks in AI 2026 Poster · Jun 2, 2026

  Fine-tuning abstractive summarization models requires high-quality annotated data. However, obtaining such corpora is expensive and time-consuming, as it requires human annotators to read and comprehend long documents to create accurate sum…

• Active Query Synthesis for Preference Learning
  Namrata Nadagouda, Nauman Ahad, Maegan Tucker, Mark A. Davenport · arXiv · May 25, 2026

  Efficient learning of user preferences is crucial for many modern decision making systems but typically requires costly labeled data. Active learning reduces this cost, yet standard methods are computationally expensive due to pool-based ev…

• Active learning accelerates electrolyte solvent screening for anode-free lithium metal batteries
  P. Ma, Ritesh Kumar, Ke-Hsin Wang, Chibueze V. Amanchukwu · Nature Communications · Sep 25, 2025

  Anode-free or ‘zero-excess’ lithium metal batteries offer high energy density compared to current lithium-ion batteries but require electrolyte innovation to extend cycle life. Due to the lack of universal design principles, electrolyte dev…

• IoT-Driven Skin Cancer Detection: Active Learning and Hyperparameter Optimization for Enhanced Accuracy.
  Jing Yang, Haoshen Qin, Jinli Wang, Por Lip Yee et al. · IEEE journal of biomedical and health informatics · Jun 10, 2025

  Skin cancer, one of the most prevalent and lethal cancer types, poses significant challenges for early diagnosis due to the diversity in lesion size, shape, color, and surface reflections. The Internet of Things (IoT) has revolutionized hea…

• AI tutoring outperforms in-class active learning: an RCT introducing a novel research-based design in an authentic educational setting
  Gregory Kestin, Kelly Miller, Anna Klales, Timothy Milbourne et al. · Scientific Reports · Jun 3, 2025

  Advances in generative artificial intelligence show great potential for improving education. Yet little is known about how this new technology should be used and how effective it can be compared to current best practices. Here we report a r…

• Charting electronic-state manifolds across molecules with multi-state learning and gap-driven dynamics via efficient and robust active learning
  M. Martyka, Lina Zhang, Fuchun Ge, Yi-Fan Hou et al. · npj Computational Materials · May 13, 2025

  We present a robust protocol for affordable learning of electronic states to accelerate photophysical and photochemical molecular simulations. The protocol solves several issues precluding the widespread use of machine learning (ML) in exci…

• Designing embodied generative artificial intelligence in mixed reality for active learning in higher education
  Andy Nguyen, Faaiz Gul, Belle Dang, Luna Huynh et al. · Innovations in Education & Teaching International · Apr 29, 2025

  ABSTRACT Generative Artificial Intelligence (GenAI) technologies have introduced significant changes to higher education, but the role of Embodied GenAI Agents in Mixed Reality (MR) environments is still relatively unexplored. This study wa…

• Efficient Process Reward Model Training via Active Learning
  Keyu Duan, Zi-Yan Liu, Xin Mao, Tianyu Pang et al. · arXiv.org · Apr 14, 2025

  Process Reward Models (PRMs) provide step-level supervision to large language models (LLMs), but scaling up training data annotation remains challenging for both humans and LLMs. To address this limitation, we propose an active learning app…

• Leveraging data mining, active learning, and domain adaptation for efficient discovery of advanced oxygen evolution electrocatalysts
  Rui Ding, Jianguo Liu, Kang Hua, Xuebin Wang et al. · Science Advances · Apr 4, 2025

  Developing advanced catalysts for acidic oxygen evolution reaction (OER) is crucial for sustainable hydrogen production. This study presents a multistage machine learning (ML) approach to streamline the discovery and optimization of complex…

• Hide and Seek in Noise Labels: Noise-Robust Collaborative Active Learning with LLMs-Powered Assistance
  Bo Yuan, Yulin Chen, Yin Zhang, Wei Jiang · Annual Meeting of the Association for Computational Linguistics · Apr 3, 2025

  Learning from noisy labels (LNL) is a challenge that arises in many real-world scenarios where collected training data can contain incorrect or corrupted labels. Most existing solutions identify noisy labels and adopt active learning to que…

• Efficient exploration of reaction pathways using reaction databases and active learning.
  Domantas Kuryla, G. Csányi, A. V. van Duin, A. Michaelides · Journal of Chemical Physics · Mar 21, 2025

  The fast and accurate simulation of chemical reactions is a major goal of computational chemistry. Recently, the pursuit of this goal has been aided by machine learning interatomic potentials (MLIPs), which provide energies and forces at qu…

• Image steganalysis using active learning and hyperparameter optimization
  Bohang Li, Ningxin Li, Jing Yang, Osama Alfarraj et al. · Scientific Reports · Mar 1, 2025

  Image steganalysis, detecting hidden data in digital images, is essential for enhancing digital security. Traditional steganalysis methods typically rely on large, pre-labeled image datasets, which are difficult and costly to compile. To ad…

• Realistic Evaluation of Deep Active Learning for Image Classification and Semantic Segmentation
  Sudhanshu Mittal, J. Niemeijer, Özgün Çiçek, Maxim Tatarchenko et al. · International Journal of Computer Vision · Feb 28, 2025
• From Selection to Generation: A Survey of LLM-based Active Learning
  Yu Xia, Subhojyoti Mukherjee, Zhouhang Xie, Junda Wu et al. · Annual Meeting of the Association for Computational Linguistics · Feb 17, 2025

  Active Learning (AL) has been a powerful paradigm for improving model efficiency and performance by selecting the most informative data points for labeling and training. In recent active learning frameworks, Large Language Models (LLMs) hav…

• Active learning framework to optimize process parameters for additive-manufactured Ti-6Al-4V with high strength and ductility
  J. Lee, Jaejung Park, Sagong Jae Man, S. Y. Ahn et al. · Nature Communications · Jan 22, 2025

  Optimizing process and heat-treatment parameters of laser powder bed fusion for producing Ti-6Al-4V alloys with high strength and ductility is crucial to meet performance demands in various applications. Nevertheless, inherent trade-offs be…

• Active Learning Strategies: A Mini Review of Evidence-Based Approaches
  Maria Eugenia Martinez, Valeria Gomez · Acta Pedagogia Asiana · Jan 17, 2025

  Active learning strategies such as think-pair-share (TPS), problem-based learning (PBL), flipped classrooms, and collaborative projects are essential for promoting student engagement, critical thinking, and academic success. This review bri…

• Implementing active learning approach to promote motivation, reduce anxiety, and shape positive attitudes: A case study of EFL learners.
  Afsheen Rezai, R. Ahmadi, Parisa Ashkani, Gholam Hossein Hosseini · Acta Psychologica · Jan 16, 2025

  Active Learning (AL) represents a transformative instructional approach that departs from traditional methods by immersing students in experiential learning activities such as problem-solving, discussions, role-plays, interactive engagement…

• Active learning and Gaussian processes for development of dissolution models: An AI-based data-efficient approach.
  Roshan A. Patel, Siddharth Kesharwani, Fady Ibrahim · Journal of Controlled Release · Jan 3, 2025

  In vitro dissolution testing plays a key role in controlling the quality and optimizing the formulation of solid dosage pharmaceutical products. Data-driven dissolution models can improve the efficiency of testing: their predictions can act…

• DIRECT: Deep Active Learning under Imbalance and Label Noise
  Shyam Nuggehalli, Jifan Zhang, Lalit K Jain, Robert D Nowak · ICLR 2025 Conference Withdrawn Submission · Sep 27, 2024

  Class imbalance is a prevalent issue in real world machine learning applications, often leading to poor performance in rare and minority classes. With an abundance of wild unlabeled data, active learning is perhaps the most effective techni…

• A Cross-Domain Benchmark for Active Learning
  Thorben Werner, Johannes Burchert, Maximilian Stubbemann, Lars Schmidt-Thieme · NeurIPS 2024 Track Datasets and Benchmarks Poster · Sep 26, 2024

  Active Learning (AL) deals with identifying the most informative samples for labeling to reduce data annotation costs for supervised learning tasks. AL research suffers from the fact that lifts from literature generalize poorly and that onl…

• Universal Rates for Active Learning
  Steve Hanneke, Amin Karbasi, Shay Moran, Grigoris Velegkas · NeurIPS 2024 poster · Sep 25, 2024

  In this work we study the problem of actively learning binary classifiers from a given concept class, i.e., learning by utilizing unlabeled data and submitting targeted queries about their labels to a domain expert. We evaluate the q…

• Learnability Matters: Active Learning for Video Captioning
  Yiqian Zhang, Buyu Liu, Jun Bao, Qiang Huang et al. · NeurIPS 2024 poster · Sep 25, 2024

  This work focuses on the active learning in video captioning. In particular, we propose to address the learnability problem in active learning, which has been brought up by collective outliers in video captioning and neglected in the litera…