Flight procedures are essential to the safety and efficiency of air traffic management. However, due to the highly specialized nature of the flight procedure design process, existing methods rely heavily on manual operations and adjustments with limited automation, resulting in inefficiencies and potential safety risks. This study introduces AutoFPDesigner, a new agent-driven approach to flight procedure design, leveraging large language models (LLMs). By utilizing multi-agent collaboration, AutoFPDesigner automates Performance-Based Navigation (PBN) procedures, enabling end-to-end automation. In this framework, the designer’s role shifts from an executor to a supervisor, issuing tasks through natural language, while the system integrates specialized knowledge and uses a toolset to complete the design. Experimental results show that procedures designed with this approach meet safety requirements nearly 100%, with 75% of tasks completed in a limited number of steps. Moreover, AutoFPDesigner performs effectively across various design tasks, outperforming existing methods. Additionally, this study conducted human interaction experiments and introduced an “instruction-based” feedback method to address agent misinterpretation of human feedback. Experimental results demonstrate that the system bridges the skill gap between experts and beginners, and that the “instruction-based” feedback method enhances the accuracy of agent feedback interpretation. Code and data are available onhttps://github.com/Zhulongtao6/AutoFPDesigner-LLM

In deep contrastive graph clustering, many methods tend to adopt a singular enhancement strategy, focusing either on structural or attribute augmentation. This limited approach constrains the model's ability to integrate multidimensional information, resulting in an imbalance in information utilization. Furthermore, the randomness involved in the selection of negative samples may lead to blurred distinctions between positive and negative samples. Therefore, we introduce a graph attention-based dual enhancement multiview clustering (GA-DE-MVC). The GA-DE-MVC first encodes structure and attributes through attention mechanisms and fully connected layers to achieve dual enhancement of structure and attributes. Then, it selects the farthest sample as the negative sample based on the Euclidean distance between cluster centers, to alleviate the randomness in negative sample selection, thereby enhancing the distinctiveness between positive and negative samples.The experimental results on six datasets surpass existing algorithms, verifying the effectiveness of the GA-DE-MVC algorithm.

Background : Code-line-level bugginess identification (CLBI) is an important area within software quality assurance, aiming to pinpoint potential buggy source code lines in a given software product. Recently, two concurrent approaches, GLANCE and DeepLineDP, have showcased impressive performance by respectively leveraging syntactic and semantic features compared with the existing state-of-the-art (SOTA) approaches in this field. Problem : Yet, the literature lacks a thorough investigation that fuses these two types of features to enhance CLBI. Such fusion holds the promise of significantly improving the efficacy of identifying defective lines. Objective : We aim to advance CLBI by fusing syntactic and semantic features, thereby harnessing their respective strengths. Method : We propose to build a CLBI approach, booSting DeePLineDP wIth syntaCtic fEatures (SPLICE) , by fusing syntactic features from GLANCE and semantic features from DeepLineDP. SPLICE comprises three variants—SPLICE-S, SPLICE-G, and SPLICE-F—each utilizing a unique line-level sorting approach. We make a comprehensive comparison with the existing SOTA approaches using six performance metrics. Result : Through an analysis of nine open source projects, our experimental results reveal that SPLICE is competitive with current SOTA CLBI approaches. Notably, SPLICE-F demonstrates superiority over all SOTA CLBI approaches, including GLANCE and DeepLineDP, across all six metrics, indicating a substantial improvement. Conclusion : This discovery underscores the critical importance of future CLBI research in fusing syntactic and semantic features to construct more effective bugginess identification approaches. It is worth noting that the analysis was conducted within the context of Java programs, which highlights the potential for exploring similar methods in other programming languages in future research.