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-z