Artificial intelligence technology is becoming increasingly essential to education. The outbreak of COVID-19 in recent years has led many schools to launch online education. Automated online assessments have become a hot topic of interest, and an increasing number of researchers are studying Automated Essay Scoring (AES). This work seeks to summarise the characteristics of current AES systems used in English writing assessment, identify their strengths and weaknesses, and finally, analyse the limits of recent studies and research trends. Search strings were used to retrieve papers on AES systems from 2018 to 2023 from four databases, 104 of which were chosen to be potential to address the posed research aims after study selection and quality evaluation. It is concluded that the existing AES systems, although achieving good results in terms of accuracy in specific contexts, are unable to meet the needs of teachers and students in real teaching scenarios. The improvements of these systems relate to the scalability of the system for assessing different topics or styles of the essays, the accuracy of the model’s predicted scores, as well as the reliability of outcomes: improving the robustness of AES models with some adversarial inputs, the richness of AES system functionality, and the development of AES assist tools.

Within the rapidly growing urban tourism industry, the development of urban landscapes plays a crucial role in shaping a city’s image and competitiveness; however, standardized and mismatched landscapes often have a negative impact, highlighting the importance of assessing urban landscape perceptions. Although existing studies have discussed this through subjective questionnaires and physiological methods, the underlying neural mechanisms have not been thoroughly explored. The research focuses on Jingdezhen, a renowned historical and cultural city in China, as its case study. Utilized the event-related potential (ERP) method to explore individuals’ perceptual consistency and neural activity toward different types of urban landscapes. We adopted a 2 (landscape type: historical, modern) X 2 (perceptual match: consistent, inconsistent) within-subject design while recording behavioral data and electrophysiological responses. The results showed that, under any condition, there were no significant differences in people’s behavioral data. Neurophysiological results indicate that consistent perceptions of modern landscapes elicited greater P200 responses, suggesting increased attention driven by visual aesthetics and emotional activation. Under conditions of perceptual inconsistency, historical landscapes elicited higher N400 amplitudes than modern landscapes, revealing cognitive conflict and effort. This study demonstrates that P200 and N400 components are effective indicators for assessing urban perception, proving the viability of the event-related potential method in urban landscape research. Additionally, the research reveals the neural mechanisms of urban environmental perception from the early stages of attention and emotional distribution to the later stages of cognitive decision-making, which involve cognitive processes from “bottom-up” to “top-down”. This study not only provides a reference for efficient design planning for those involved in urban science but also inspires the coordination between the developmental needs of historical and modern urban landscapes. Moreover, it offers a new perspective for an interdisciplinary approach to urban perception assessment.

Automated Essay Scoring (AES) systems increasingly leverage fine-tuned large language models (LLMs) to enhance scoring accuracy and feedback generation. However, current LLM-based AES approaches often lack interpretability and consistent alignment with human scoring rubrics, limiting their practical adoption in educational settings. This study proposes QwenScore+, a novel framework that integrates rubric-aware Chain-of-Thought (CoT) prompting with reinforcement learning from human feedback (RLHF) to improve the transparency, quality, and educational alignment of automated feedback. QwenScore+ is evaluated on a proprietary IELTS writing dataset comprising over 5,000 essays annotated with trait-level scores and expert-written feedback. Experimental results demonstrate that QwenScore+ significantly outperforms strong baselines such as BERT, GPT-3.5, and GPT-4 in feedback generation, achieving higher BLEU, ROUGE-L, and cosine similarity scores, alongside improvements in trait-level scoring measured by quadratic weighted kappa (QWK). Furthermore, rubric-aligned CoT prompting enables the generation of feedback that better mirrors human reasoning patterns, as confirmed through automatic metrics and human evaluations. These findings highlight the potential of combining explainable reasoning strategies with human-aligned reward optimization to develop more transparent, reliable, and pedagogically valuable AES systems for real-world applications.

Urban Green Spaces (UGS) are integral components of the built environment, significantly contributing to its ecological, social, and performance dimensions, including microclimate regulation, occupant well-being, and energy efficiency. This decadal review (2015–2025) systematically analyzes 70 high-impact studies to propose a “Symbiotic Intelligence” framework. This framework integrates Generative AI, ethical algorithms, and innovations from the Global South to revolutionize the planning, design, and management of UGS within building landscapes and urban fabrics. Our analysis reveals that Generative AI can optimize participatory design processes and generate efficient planning schemes, increasing public satisfaction by 41% and achieving fivefold efficiency gains. Metaverse digital twins enable high-fidelity simulation of UGS performance with a mere 3.2% error rate, providing robust tools for building environment analysis. Ethical algorithms, employing fairness metrics and SHAP values, are pivotal for equitable resource distribution, having been shown to reduce UGS allocation disparities in low-income communities by 67%. Meanwhile, innovations from the Global South, such as lightweight federated learning and low-cost sensors, offer scalable solutions for building-environment monitoring under resource constraints, reducing model generalization error by 18% and decreasing data acquisition costs by 90%. However, persistent challenges-including data heterogeneity, algorithmic opacity (with only 23% of studies adopting interpretability tools), and significant data gaps in the Global South (coverage < 15%)-hinder equitable progress. Future research should prioritize developing UGS-climate-building coupling models, decentralized federated frameworks for building management systems, and blockchain-based participatory planning to establish a more robust foundation for sustainable built environments. This study provides an interdisciplinary roadmap for integrating intelligent UGS into building practices, contributing to the advancement of green buildings, occupant-centric design, and the overall sustainability and resilience of our built environment.

Presents corrections to the paper, (Corrections to “A Systematic Literature Review: Are Automated Essay Scoring Systems Competent in Real-Life Education Scenarios?”).