Li-rich Mn-based layered oxides (LRMO) provide high capacity, but operation above 4.5 V is constrained by a transport-stability conflict: carbonate-rich Li⁺ coordination supports ion conduction while delivering reactive solvent molecules to an oxygen-redox-active cathode and a Li-metal anode. Here, a carbonate electrolyte containing 1,1,2,2-tetrafluoroethyl-2,2,3,3-tetrafluoropropyl ether (HFE), 1,3,6-hexanetricarbonitrile (HTCN), and trace LiNO₃ is used to regulate how Li⁺-containing species pass through the outer and inner Helmholtz layers. Molecular dynamics, Raman/NMR spectroscopy, in situ Raman tracking, and interfacial electrochemical measurements show that HFE weakens Li⁺-carbonate coordination and enriches fluorinated species near electrified surfaces. This environment allows HTCN to remain transiently associated with incoming Li⁺ clusters through the outer Helmholtz plane (OHP) and to become available near LRMO during partial desolvation, where nitrile-derived species participate in cathode electrolyte interphase (CEI) formation. At Li metal, reduced carbonate competition allows trace nitrate to enter the earliest reduction events in the inner Helmholtz plane (IHP). The resulting N/F-rich CEI and Li₃N/LiF-rich solid electrolyte interphase (SEI) suppress gas evolution, transition-metal dissolution, and nonuniform Li growth. LRMO cells cycled to 4.8 V deliver 276.9 mAh·g^–1 and retain 85.43% after 200 cycles at 0.1 C, demonstrating coordinated dual-interface regulation for high-voltage lithium batteries.

With the widespread use of lithium-ion batteries in electric vehicles, energy storage, and mobile terminals, there is an urgent need to develop cathode materials with specific properties. However, existing material control synthesis routes based on repetitive experiments are often costly and inefficient, which is unsuitable for the broader application of novel materials. The development of machine learning and its combination with materials design offers a potential pathway for optimizing materials. Here, we present a design synthesis paradigm for developing high energy Ni-rich cathodes with thermal/kinetic simulation and propose a coupled image-morphology machine learning model. The paradigm can accurately predict the reaction conditions required for synthesizing cathode precursors with specific morphologies, helping to shorten the experimental duration and costs. After the model-guided design synthesis, cathode materials with different morphological characteristics can be obtained, and the best shows a high discharge capacity of 206 mAh g⁻¹ at 0.1C and 83% capacity retention after 200 cycles. This work provides guidance for designing cathode materials for lithium-ion batteries, which may point the way to a fast and cost-effective direction for controlling the morphology of all types of particles.

Poly (ethylene oxide) (PEO)-based polymer electrolytes show the prospect in all-solid-state lithium metal batteries; however, they present limitations of low room-temperature ionic conductivity, and interfacial incompatibility with high voltage cathodes. Therefore, a salt engineering of 1, 1, 2, 2, 3, 3-hexafluoropropane-1, 3-disulfonimide lithium salt (LiHFDF)/LiTFSI system was developed in PEO-based electrolyte, demonstrating to effectively regulate Li ion transport and improve the interfacial stability under high voltage. We show, by manipulating the interaction between PEO matrix and TFSI⁻-HFDF⁻, the optimized solid-state polymer electrolyte achieves maximum Li⁺ conduction of 1.24 × 10⁻⁴ S cm⁻¹ at 40 °C, which is almost 3 times of the baseline. Also, the optimized polymer electrolyte demonstrates outstanding stable cycling in the LiFePO₄/Li and LiNi_0.8Mn_0.1Co_0.1O₂/Li (3.0–4.4 V, 200 cycles) based all-solid-state lithium batteries at 40 °C.