Perovskite oxides with the ABO₃ structure are core candidates for dielectric energy-storage capacitors, whose recoverable energy density is governed by the dielectric constant, the breakdown field strength, and the nonlinear polarization response. This review surveys recent machine-learning studies on predicting these properties of oxide perovskites, covering three representative quantities—the dielectric constant, the breakdown field strength, and the ferroelectric Curie temperature—together with direct performance indicators such as recoverable energy density and efficiency. The works are compared along the evolution of methods, from manual descriptors and ensemble learning to graph neural networks, small-sample strategies, and generative inverse design, with dataset size, verification level, and accuracy documented. Three insights emerge: physical descriptor models remain competitive and interpretable under small-sample conditions; equivariant graph neural networks offer advantages for tensorial and finite-temperature tasks at higher data and computational cost; and generative inverse design is emerging, with preliminary success at the ferroelectric mesoscopic scale, but remains limited by scarce multimodal data and incomplete experimental-validation loops, which constitute the main challenges ahead.

Show more

Nowadays, lithium-ion batteries (LIBs) are widely used in portable electronics, electric vehicles, and grid-scale energy storage systems. However, the commercial graphite anode has almost reached its theoretical capacity limit of 372 mAh g⁻¹, and conventional cathode materials still face problems such as low specific capacity and unstable electrode-electrolyte interfaces, which limit the cycle life and safety of the batteries. Nanotechnology can provide useful ways to deal with these problems, because it shortens the diffusion path of lithium ions, buffers the volume strain during charge and discharge, and stabilizes the interfacial chemistry between electrode and electrolyte. This paper reviews the recent development of nanotechnology in both cathode and anode materials. For cathode materials, elemental doping can stabilize the crystal lattice and improve ion transport, surface coatings can reduce the dissolution of transition metals and side reactions with the electrolyte, and morphology control can further shorten diffusion paths and improve rate capability. For anode materials, carbon coating, porous structures, and one-dimensional nanowires can relieve volume expansion and make the solid-electrolyte interphase more stable. This review also discusses several key challenges, such as nanoparticle agglomeration, side reactions at the interface, and manufacturing cost, and gives some prospects for future multi-scale synergistic design.

Show more

DeepSeek AI research team made breakthrough progress in verifiable reasoning tasks such as mathematics and code by using rule verification rewards in coordination with group relative policy optimization (GRPO), but reliable reward models are difficult to build on tasks such as writing, and the risk of Reward Hacking still exists outside the verifiable field. Taking DeepSeek-R1 as an anchor, this paper summarizes the progress of detection and mitigation of Reward Hacking from four aspects: formal definition, data set and evaluation indicators, method level, limitations and response. This paper first combs the formal definition of Reward Hacking and the classification framework under the assumption of proxy compression; Then, typical data sets and evaluation indicators are introduced, and the level of task performance and detection mitigation achieved by current mainstream methods is summarized; Finally, the structure boundary of rule reward, the algorithm layer performance of GRPO deviation, and the direction of detection and mitigation are analyzed. The overview shows that Reward Hacking originates from information compression in agent reward optimization, which can verify that accurate rules in the domain can compress Reward Hacking space, while outside the domain, it needs to rely on a collaborative system consisting of KL monitoring, representation detection, algorithm correction and policy constraints.

Show more

With the accelerating intelligent transformation of global manufacturing, industrial robots have become critical equipment in modern smart factories. However, the growing prevalence of multi-variety, small-batch production has made the high programming threshold, tedious reconfiguration, and limited environmental adaptability of traditional industrial robots increasingly prominent. Over the past few years, large language models (LLMs) have proven to have strong semantic comprehension, knowledge reasoning, and task planning abilities, a new avenue in the intelligent upgrading of industrial robots. The systematic review of the literature on the topic of the industrial robot driven by LLM is presented in this paper, including the mainstream technical directions, and the representative studies in five areas of application: industrial inspection, assembly and collaboration, maintenance and fault recovery, manufacturing operation planning, and robot navigation. Based on this, the paper examines the key challenges to be addressed at present, including model output reliability and safety, the simulation-to-reality gap and real-time constraints, and data scarcity and distribution shift. It also discusses future research opportunities, including knowledge enrichment and reliable reasoning, lightweight deployment and edge computing, and life-long learning and domain adaptation. The purpose of this paper is to serve as a reference in future studies and implementation of LLMs in industrial robots.

Show more