AI coding agents are increasingly contributing to software development, yet their impact on mobile development has received little empirical attention. In this paper, we present the first category-level empirical study of agent-generated code in open-source mobile app projects. We analyzed PR acceptance behaviors across mobile platforms, agents, and task categories using 2,901 AI-authored pull requests (PRs) in 193 verified Android and iOS open-source GitHub repositories in the AIDev dataset. We find that Android projects have received 2x more AI-authored PRs and have achieved higher PR acceptance rate (71%) than iOS (63%), with significant agent-level variation on Android. Across task categories, PRs with routine tasks (feature, fix, and ui) achieve the highest acceptance, while structural changes like refactor and build achieve lower success and longer resolution times. Furthermore, our evolution analysis shows improvement in PR resolution time on Android through mid-2025 before it declined again. Our findings offer the first evidence-based characterization of AI agents effects on OSS mobile projects and establish empirical baselines for evaluating agent-generated contributions to design platform aware agentic systems.

The classical game theory provides a useful tool to analyze the agent’s (or player’s) behavior, often limited to binary choices, i.e., cooperation or defection. However, real-world agent behavior is typically nuanced. This article leverages a continuous action iterated dilemma (CAID) framework, allowing players to adopt a varied range of strategies between two binary decisions. Moreover, most studies presume all agents to have perfect communication networks, neglecting the complexities of real-world networks, such as delays, model uncertainties, and information losses. In this regard, this work presents a new exact-time (ExT) convergent CAID strategy, considering the communication delays during data transmission and information loss in complex networks. The conventional convergence analysis typically relies on Jacobian matrices, which consider a strong correlation between players and, therefore, struggle when dealing with complex player relationships. In contrast, the proposed ExT algorithm ensures consensus among all players, irrespective of the initial conditions, within a preset time selected by the user. The CAID model’s convergence is analyzed using Lyapunov theory and Artstein’s transformation, which validates the ExT convergence to the consensus value amidst communication delays and information loss. Extensive simulations reveal that the proposed strategy consistently outperforms existing methods in terms of convergence speed.

Airport taxi delays pose significant challenges to airlines, passengers, and environmental sustainability. Addressing these delays requires synchronizing uncertain airside operations, including pushback sequencing, taxiway movements, and runway take-offs. This article presents the intelligent departure metering advisory tool (I-MATE), an artificial intelligence (AI)-based decision support system that recommends pushback timings to air traffic controllers (ATCOs) to reduce taxi delays while balancing downstream runway throughput. I-MATE's recommendation outcomes unfold over a longer time horizon compared to other AI-driven decision support systems in air traffic control, such as conflict resolution tools, posing a greater cognitive challenge for ATCOs. We conducted validation experiments to assess the efficacy and acceptability of I-MATE in assisting ATCOs to manage airside traffic. The study revealed a spectrum of compliance with I-MATE recommendations among ATCOs, highlighting the complex interplay between human behavior and AI-driven decision support systems. While ATCOs rated I-MATE highly for usefulness and reliability, concerns regarding transparency and explainability emerged. ATCO feedback also emphasized the importance of considering individual differences and human factors in the design of such systems. This research underscores the value of AI-based decision support systems in complex, dynamic environments, particularly for addressing the cognitive challenge of balancing long-term outcomes with immediate actions.

Airside taxi delays have adverse consequences for airports and airlines globally, leading to airside congestion, increased Air Traffic Controller/Pilot workloads, missed passenger connections, and adverse environmental impact due to excessive fuel consumption. Effectively addressing taxi delays necessitates the synchronization of stochastic and uncertain airside operations, encompassing aircraft pushbacks, taxiway movements, and runway take-offs. With the implementation of mixed-mode runway operations (arrivals-departures on the same runway) to accommodate projected traffic growth, complexity of airside operations is expected to increase significantly. To manage airside congestion under increased traffic demand, development of efficient pushback control, also known as Departure Metering (DM), policies is a challenging problem. DM is an airside congestion management procedure that controls departure pushback timings, aiming to reduce taxi delays by transferring taxiway waiting times to gates. Under mixed-mode runway operations, however, DM must additionally maintain sufficient runway pressure—departure queues near runway for take-offs—to utilize available departure slots within incoming arrival aircraft steams. While a high pushback rate may result in extended departure queues, leading to increased taxi-out delays, a low pushback rate can result in empty slots between incoming arrival streams, leading to reduced runway throughput. This study introduces a Deep Reinforcement Learning (DRL) based DM approach for mixed-mode runway operations. We cast the DM problem in a markov decision process framework and use Singapore Changi Airport surface movement data to simulate airside operations and evaluate different DM policies. Predictive airside hotspots are identified using a spatial-temporal event graph, serving as the observation to the DRL agent. Our DRL-based DM approach utilizes pushback rate as agent’s action and reward shaping to dynamically regulate pushback rates for improved runway utilization and taxi delay management under uncertainties. Benchmarking the learnt DRL-based DM policy against other baselines demonstrates the superior performance of our method, especially in high traffic density scenarios. During a typical day at Singapore Changi Airport, DRL-based DM reduces peak taxi times by 1-3 minutes on average, saves 26.6% in fuel consumption, and contributes to more environmentally friendly and sustainable airside operations.

Video memorability prediction has become an important research topic in computer vision in recent years. The movie's input is highly remembered that gains much attention with unbounded time constraints. Episodic memory is a fascinating research area that needs much attention using video processing tools and techniques. Episodic memories are long-lasting with complete detail. Movies are one of the best instances of episodic memory. This paper proposes a novel framework to fuse deep features to predict the probability of recalling episodic events. Memories are reproducible and sensitive to sophisticated set of properties rather than low-level propertiesthe proposed framework pin up the fusion of text, visual and motion features. A fuzzy-based FastText model, a supervised text extraction module, is designed to extract the annotations with their relevant classes. The colour histogram analysis is done to determine the dominant colour region that performs as a connected fragment to form episodic video sequences. A novel Faster R-CNN is designed to discover the scene objects using an informative regional proposal network formation. Here, the modified loss function sorts out the lowest overlapping regions yielding the best proposals. The ‘high-level’ properties are collected using Principal Component Analysis (PCA) to form episodic shots. These are fused to estimate the memorability score. The proposed framework is implemented in Mediaeval 2018 datasets. A superior spearman's rank correlation result is achieved as 0.6428 short-term and 0.4285 long-term memorability than the latest comparable methods.

Airport taxi delays adversely affect airports and airlines around the world leading to airside congestion, increased Air Traffic Controllers/Pilot workload, and adverse environmental impact due to excessive fuel burn. Airport Departure Metering (DM) is an effective approach to contain taxi delays by controlling departure pushback timings. The key idea behind DM is to transfer aircraft waiting time from taxiways to gates. State-of-the-art DM methods use model-based control policies that rely on airside departure modeling to obtain simplified analytical equations. Consequently, these models fail to capture non-stationarity in the airside operations leading to poor performance of control policies under uncertainties. This work proposes model-free and learning-based DM using Deep Reinforcement Learning (DRL) approach to reduce taxi delays while meeting flight schedule constraints. This paper casts the DM problem in a markov decision process framework and develops a representative airport-airside simulator to simulate airside operations and evaluate the learnt DM policy. For effective state representation, this work introduces taxiway hotspot features to account for the spatial-temporal evolution of airside congestion levels. This significantly improves the DM policy convergence rate during training. The performance of the learnt policy is evaluated under different traffic densities with a reduction of approximately 44% in taxi out delays, in medium-density traffic scenarios, which corresponds to 2-minute savings in taxi-out time per aircraft. Furthermore, benchmarking DRL against an evolutionary method and another state-of-the-art simulation-based heuristic demonstrates the superior performance of our method, especially in high traffic density scenarios. With increased traffic density, taxi-time savings achieved by the learnt DM policy increase without a significant decrease in runway throughput. Results, on a typical day of simulated operations at Singapore Changi Airport, demonstrate that DRL can learn an effective DM policy to contain congestion on the taxiways, reduce total fuel consumption by approximately 22% and better manage the airside traffic.