Feed status
41 parsed articles
Last update: 2026-09-22
2026-09-18
Living organisms continuously monitor their internal physiological states while interacting with complex environments and adapt their actions in response to changes in these internal signals. New work combines such biological principles with cybernetics, reinforcement learning and neuroscience to develop a framework for autonomous and adaptive artificial embodied agents.
DOI: 10.1038/s42256-026-01312-x2026-09-14
Ruocheng Wang, Xiaoqiu Zhong, Zhuo Xia, Junchi Yan
DOI: 10.1038/s42256-026-01314-92026-09-10
Tongyu Shi, Yutang Li, Zhanyuan Li, Qian Liu, Jie Zhou, Wenhe Xu, Yang Li, Dawei Dai, Rui He, Wenhua Zhou, Jiahong Wang, Xue-Feng Yu
Shi et al. demonstrate a dual architecture approach for materials research, integrating two lightweight large language models for collaborative reasoning and scientific tool execution. The method achieves competitive performance while remaining affordable and locally deployable.
DOI: 10.1038/s42256-026-01298-62026-09-07
Dharshan Kumaran, Nathaniel Daw, Simon Osindero, Petar Veličković, Viorica Patraucean
Kumaran et al. show that large language models making decisions on when to answer a question or abstain from answering can be influenced by boosting or suppressing confidence signals in the model.
DOI: 10.1038/s42256-026-01293-x2026-09-03
Ruocheng Wang, Xiaoqiu Zhong, Zhuo Xia, Junchi Yan
Wang et al. introduce a hardware-efficient quantum neural operator that overcomes classical linear capacity limits. Using an implicit quadratic frame, it offers accelerated expressivity for solving differential equations in the noisy intermediate-scale quantum era.
DOI: 10.1038/s42256-026-01289-72026-09-03
Utkarsh Upadhyay, Julian Herold, Markus Götz, Alexander Schug
RNA structure and function are hard to infer because annotations are scarce, despite abundant sequence data. Upadhyay et al. trained a self-supervised model on large-scale RNA data that derives biologically meaningful patterns from sequence correlations.
DOI: 10.1038/s42256-026-01295-92026-09-01
Messi H. J. Lee, Calvin K. Lai
Lee and Lai study bias-like processing differences in large language reasoning models and find that, for most models, processing stereotypical information takes less computational effort than processing counter-stereotypical information.
DOI: 10.1038/s42256-026-01300-12026-09-01
Changde Du, Huiguang He
Representational alignment can reveal similarities between human brain activity and language models. Work now demonstrates that it can also guide learning, improving the reliability of artificial reasoning.
DOI: 10.1038/s42256-026-01302-z2026-07-24
Yubin Kim
Nature Machine Intelligence, Published online: 24 July 2026; doi:10.1038/s42256-026-01268-y A controlled study of large language model agents across 260 configurations shows when multi-agent collaboration helps or hurts performance, and introduces a predictive model that selects the best architecture in 87% of held-out within-domain configurations.]]>
DOI: 10.1038/s42256-026-01268-y2026-07-24
Nature Machine Intelligence, Published online: 24 July 2026; doi:10.1038/s42256-026-01288-8 Training machine learning models on high-quality biological datasets can quickly produce abundant results. But as datasets often evolve over time, further work is required to update models and maintain alignment between models and datasets.]]>
DOI: 10.1038/s42256-026-01288-82026-07-21
Hui Lin
Nature Machine Intelligence, Published online: 21 July 2026; doi:10.1038/s42256-026-01254-4 Lin et al. introduce a brain-inspired generative model that provides two key features of intelligence: planning and problem-solving. It uses cognitive maps, stochastic computing and compositional coding, and requires only local synaptic plasticity.]]>
DOI: 10.1038/s42256-026-01254-42026-07-20
Moufan Li
Nature Machine Intelligence, Published online: 20 July 2026; doi:10.1038/s42256-026-01274-0 Li et al. show that recurrent neural networks optimized for free recall discover diverse, human-like memory strategies beyond classical temporal context models, with top models using an index-based mechanism resembling the memory palace technique.]]>
DOI: 10.1038/s42256-026-01274-02026-07-15
Gianluca Fabiani
Nature Machine Intelligence, Published online: 15 July 2026; doi:10.1038/s42256-026-01265-1 Moving beyond brute-force simulations, local neural operators—combined with equation-free methods and Krylov subspace techniques—enable system-level stability and bifurcation analysis of complex spatiotemporal systems directly from data.]]>
DOI: 10.1038/s42256-026-01265-12026-07-14
Rundong Feng
Nature Machine Intelligence, Published online: 14 July 2026; doi:10.1038/s42256-026-01271-3 Realigning AI technology towards the Sustainable Development Goals]]>
DOI: 10.1038/s42256-026-01271-32026-07-14
David Klindt
Nature Machine Intelligence, Published online: 14 July 2026; doi:10.1038/s42256-026-01259-z Kindt et al. present a unifying framework for superposition in neural networks. Their three-step approach clarifies how latent features can be identified, disentangled and assessed.]]>
DOI: 10.1038/s42256-026-01259-z2026-07-13
S. Song
Nature Machine Intelligence, Published online: 13 July 2026; doi:10.1038/s42256-026-01260-6 Song et al. propose Sustainability Robotics as a new discipline to overcome fragmentation and enhance societal and environmental impact. They define three guiding principles, alongside two dimensions spanning sustainable design and robotics for sustainability.]]>
DOI: 10.1038/s42256-026-01260-62026-07-13
Peyton Chandarana
Nature Machine Intelligence, Published online: 13 July 2026; doi:10.1038/s42256-026-01273-1 The brain’s architecture exhibits diversity across many temporal and spatial scales, yet our computing architectures remain largely homogeneous. Low-powered neuromorphic hardware offers a path towards energy-efficient AI, but could these approaches be improved with heterogeneous computing architectures?]]>
DOI: 10.1038/s42256-026-01273-12026-07-03
Julius Berner
Nature Machine Intelligence, Published online: 03 July 2026; doi:10.1038/s42256-026-01267-z Berner et al. show how to adapt popular neural networks into discretization-agnostic neural operators that learn from continuous scientific data, enabling scientific simulations that generalize more reliably across resolutions.]]>
DOI: 10.1038/s42256-026-01267-z2026-07-02
Zifeng Wang
Nature Machine Intelligence, Published online: 02 July 2026; doi:10.1038/s42256-026-01266-0 Wang et al. develop DeepEvidence, a biomedical deep research agent for exploring and synthesizing evidence across various knowledge sources to support drug discovery, clinical trials and evidence-based medicine.]]>
DOI: 10.1038/s42256-026-01266-02026-06-22
Xuanyu An
Nature Machine Intelligence, Published online: 22 June 2026; doi:10.1038/s42256-026-01252-6 An, Luo, Zhang and colleagues present Turbo, a transformer-based reinforcement learning framework that enables simulation-to-real transfer for autonomous navigation and obstacle avoidance in physical microrobotic swarms operating in unknown environments.]]>
DOI: 10.1038/s42256-026-01252-62026-06-12
Jiyeong Kim
Nature Machine Intelligence, Published online: 12 June 2026; doi:10.1038/s42256-026-01256-2 Psychiatric disorders are heterogeneous, and care depends on interpreting unstructured longitudinal narratives, creating variability that hinders standardization. A study now shows that a psychiatry-specific large language model (LLM) may help clinicians to deliver more consistent, high-quality care.]]>
DOI: 10.1038/s42256-026-01256-22026-06-11
Jiacheng Xiong
Nature Machine Intelligence, Published online: 11 June 2026; doi:10.1038/s42256-026-01250-8 Xiong et al. introduce ConfSeq, a molecular conformation description language that enables language models to perform three-dimensional molecular modelling tasks, including conformer prediction, three-dimensional molecular generation and representation, with strong performance.]]>
DOI: 10.1038/s42256-026-01250-82026-06-11
Margarida Victoriano
Nature Machine Intelligence, Published online: 11 June 2026; doi:10.1038/s42256-026-01244-6 Synthetic datasets are becoming crucial for the development of biomedical machine learning models. Victoriano et al. discuss the persistent simulation-to-reality gap that limits how well synthetic performance predicts real-world performance.]]>
DOI: 10.1038/s42256-026-01244-62026-06-10
Chonghuan Zhang
Nature Machine Intelligence, Published online: 10 June 2026; doi:10.1038/s42256-026-01257-1 Based on independent reproduction and external benchmarks, this study shows that RXNGraphormer is reproducible and transferable across reaction prediction tasks, while revealing limitations under heterogeneous and distribution-shifted settings.]]>
DOI: 10.1038/s42256-026-01257-12026-06-09
Anna Tomberg
Nature Machine Intelligence, Published online: 09 June 2026; doi:10.1038/s42256-026-01251-7 Machine learning methods for drug discovery often face difficulties in identifying novel bioactive molecules that do not belong to the training data distribution. A new metric can now quantify chemical distribution shift and evaluate the generalization capability of molecular machine learning models.]]>
DOI: 10.1038/s42256-026-01251-72026-05-27
Rong Han
Nature Machine Intelligence, Published online: 27 May 2026; doi:10.1038/s42256-026-01243-7 Han et al. introduce UniAIR, a unified AI framework that predicts mutation effects across diverse immune recognition settings. The approach enables more generalizable modelling of antibody, antigen and T cell receptor interactions.]]>
DOI: 10.1038/s42256-026-01243-72026-05-25
Jiale Zhao
Nature Machine Intelligence, Published online: 25 May 2026; doi:10.1038/s42256-026-01234-8 pUniFind is a large-scale deep learning model for proteomics that unifies peptide–spectrum scoring and open de novo sequencing. Trained on over 100 million spectra, it substantially improves peptide identification and modification discovery.]]>
DOI: 10.1038/s42256-026-01234-82026-05-18
Xianyong Wang
Nature Machine Intelligence, Published online: 18 May 2026; doi:10.1038/s42256-026-01246-4 SpecGP enhances fragment ion coverage to enable the prediction of N-glycopeptide structural spectra across diverse collision energies, thereby improving isomer discrimination and boosting identification confidence through rescoring.]]>
DOI: 10.1038/s42256-026-01246-42026-05-18
David Resnik
Nature Machine Intelligence, Published online: 18 May 2026; doi:10.1038/s42256-026-01247-3 Generative artificial intelligence (GenAI) tools are challenging our understanding of plagiarism. How should we deal with plagiarism of ideas if this misbehaviour is increasingly common, and it is extremely difficult to prove when GenAI is involved? Definitions of research misconduct that specifically address the use of GenAI tools are needed.]]>
DOI: 10.1038/s42256-026-01247-32026-05-18
Nature Machine Intelligence, Published online: 18 May 2026; doi:10.1038/s42256-026-01253-5 Companies, tech workers and researchers are in a frenzy to embed agentic AI into their workflows, locked in a self-imposed race not to fall behind. There must be a better way to make use of AI technology.]]>
DOI: 10.1038/s42256-026-01253-5