Published in Engineering, this study introduces HCGCDM, an LLM-powered cognitive diagnosis model built on heterogeneous concept graphs. Unlike traditional tools that only capture prerequisite knowledge links, it automatically mines three types of concept relations via RAG. Tailored graph encoders and adaptive weighting boost student proficiency assessment accuracy, with ablation and LLM comparison experiments verifying its effectiveness and the impact of LLM capability on diagnostic performance.

Published in Engineering, this report introduces LLM-IDA, a three-tier multi-agent LLM framework for automated industrial design. It divides design workflows into four functional modules to address LLM hallucination and poor robustness via closed-loop code generation and self-verification. Benchmarked against RAG with pass@10 metrics and ablation tests, the modular system cuts manual engineering overhead and supports cross-domain mechanical design optimization, with its current limits and future research directions covered.

Published in Engineering, this news report covers a comprehensive survey exploring how large language models tackle long-standing flaws in two mainstream autonomous driving frameworks: modularized pipelines and end-to-end neural networks. It details LLM applications across perception, prediction, planning and data construction, lists core deployment barriers like hallucination and latency, and unpacks ongoing debates over AGI and the future architecture of intelligent driving systems.

Traditional manual design of Earth Observation Satellite Scheduling Problem algorithms costs massive expert labor. This research introduces AgentAD, an LLM-powered five-agent collaborative framework that converts natural language scenario descriptions into executable Python scheduling codes via four sequential phases. Tests prove its self-evolved algorithms outperform mainstream human-designed heuristics, with memory stream and chain-of-coding mechanisms stabilizing iterative optimization for both basic and complex satellite task scenarios.

Tired of slow, inflexible wind farm maintenance scheduling? New research published in Engineering presents LLM4M, a dedicated fine-tuned language model for turbine repair planning. It quickly generates cost-efficient crew routes with tiny errors versus mathematical optimal solutions, beating popular general LLMs. It runs offline on ordinary hardware and adapts to dynamic real-time maintenance tasks, while its discovered performance phase transition offers practical tips for training industry-specific AI models.

Published in Engineering, this review systematically sorts interdisciplinary engineering therapies for spinal cord injury. It analyzes the three-stage secondary pathological cascade after trauma and elaborates five core intervention branches including neuromodulation, cell transplantation, and functional biomaterials. The article also identifies major translational obstacles and advocates integrated multimodal treatment plus cross-field cooperation to speed clinical transformation of SCI repair technologies.

A newly published review in Engineering defines mitochondrial deacetylase SIRT3 as the core ‘‘head goose molecule’’ triggering negentropic mechanisms to reverse diabetes, obesity, and steatotic liver disease. It sorts three classes of SIRT3 activators and notes translational hurdles, providing systematic theoretical support for targeted metabolic disease therapies.

This report covers a single-cell RNA sequencing study published in *Engineering*, exploring how dietary phytosterol oxidation products (POPs) trigger aortic inflammation in atherosclerosis. The paper identifies 7-ketositosterol (7-KS), the major food-derived POP, drives macrophage M1 polarization via the TLR4–IRF5 signaling axis. Mouse assays and public human arterial single-cell datasets verify this conserved inflammatory molecular signature, offering a single-cell research paradigm for dietary lipid-related cardiovascular disease.