This paper presents AudioSamples, an audio processing system that treats audio as a first-class data type rather than as generic numerical arrays accompanied by externally managed metadata. In many existing libraries, researchers must manually propagate sampling parameters such as sample rate, channel layout, and format across function calls, introducing cognitive overhead, silent error modes, and reproducibility risks. AudioSamples eliminates this coordination burden by embedding semantic properties directly within the audio object and automatically preserving them across processing pipelines, while requiring explicit and well-defined conversions when semantics change.

In this article, we propose Cross-Modal Association Models (C-MAMs), a novel approach for handling missing modalities during inference in multimodal learning. Unlike existing methods that modify the training process, C-MAMs generate missing modality features post-training , preserving the integrity of the original multimodal model. In this article, we: (i) formalise the problem of missing modality inference and its challenges, (ii) introduce C-MAMs as a flexible, lightweight, post-hoc solution for reconstructing missing modality embeddings, (iii) evaluate their effectiveness across diverse datasets, tasks and baseline models, and (iv) analyse the quality of the generated versus the ground-truth features to quantify the reconstruction fidelity. Experimental results show that C-MAMs significantly mitigate performance degradation due to missing modalities, in some cases fully restoring baseline performance, even when trained on 10% of the data. We conclude that post-training feature reconstruction is an effective, targeted alternative to existing methods, with broad applicability in multimodal systems.

The proliferation of ultra-low-latency and faster convergence applications in sixth-generation (6G) networks necessitates mobile edge computing (MEC) for offloading computationally intensive tasks from user devices to the network edge. However, traditional offloading approaches ignore the semantic aspects of tasks and resources. This paper proposes a novel ontology-based reinforcement learning (ORL) approach for optimal semantic offloading decisions in evolving dynamic MEC-enabled 6G networks, considering network uncertainty and time variation conditions. The proposed ORL approach integrates a dynamic learning mechanism that adjusts and captures semantics task resources, enabling adaptive real-time offloading decisions to satisfy task processing requirements and user demands. The numerical results demonstrate significant improvements in latency reduction, responsiveness, and adaptability compared to traditional offloading approaches.

Abstract In multi-agent systems, goal achievement is challenging when agents operate in ever-changing environments and face unseen situations, where not all the goals are known or predefined. In such cases, agents need to identify the changes and adapt their behaviour, by evolving their goals or even generating new goals to address the emerging requirements. Learning and practical reasoning techniques have been used to enable agents with limited knowledge to adapt to new circumstances. However, they depend on the availability of large amounts of data, require long exploration periods, and cannot help agents to set new goals. Furthermore, the accuracy of agents’ actions is improved by introducing added intelligence through integrating conceptual features extracted from ontologies. However, the concerns related to taking suitable actions when unseen situations occur are not addressed. This paper proposes a new Automatic Goal Generation Model (AGGM) that enables agents to create new goals to handle unseen situations and to adapt to their ever-changing environment on a real-time basis. AGGM is compared to Q-learning, SARSA, and Deep Q Network in a Traffic Signal Control System case study. The results show that AGGM outperforms the baseline algorithms in unseen situations while handling the seen situations as well as the baseline algorithms.

Edge computing is a promising paradigm that can address the requirements of compute-intensive tasks generated by delay-sensitive applications, through bringing processing and storage to the edge of the network. Task offloading is challenging in open and dynamic environments where applications with various Service Level Agreement (SLA) and Quality of Service (QoS) requirements frequently produce a fluctuated workload at the edge of a network with heterogeneous, mobile, and geodistributed nodes.The current literature has addressed this challenge by offloading tasks to fog or Mobile Edge Computing (MEC) servers. However, in strictly delay-sensitive applications such as augmented reality, autonomous driving, or remote surgery, a Pure Edge Computing (PEC) paradigm that allows peer-to-peer communication and cooperation is more reasonable.This paper proposes a novel learning-based task offloading model that enables a pure edge-based system with mobile and resource-constrained nodes to accommodate fluctuating workload generated by applications with various SLAs and QoS. The results show a better utilization of resources and tasks success rate when compared to the state-of-the-art algorithms.

Agents frequently collaborate to achieve a shared goal or to accomplish a task that they cannot do alone. However, collaboration is difficult in open multi-agent systems where agents share constrained resources to achieve both individual and shared goals. In current approaches to collaboration, agents are organised into disjoint groups and social reasoning is used to capture their capabilities when selecting a qualified set of collaborators. These approaches are not useful when agents are in multiple, overlapping groups; depend on each other when using shared resources; have multiple goals to achieve simultaneously; and have to share the overall costs and benefits. In this article, agents use social reasoning to enhance their understanding of other agents’ goals and their dependencies, and self-adaptive techniques to adapt their level of self-interest in a collaborative process, with a view to contributing to lowering shared costs or increasing shared benefits. This model aims at improving the extent to which agents’ goals are met while improving shared resource usage efficiency. For example, in a public transport system where each mode of transport has limited capacity, commuters will be enabled to make choices that avoid over-capacity in different modes, or in a smart energy grid with limited capacity, users can make choices as to when they increase their demand. The model simultaneously helps avoid overloading a shared resource while allowing users to achieve their own goals. The proposed model is evaluated in an open multi-agent system with 100 agents operating in multiple overlapping groups and sharing multiple constrained resources. The impact of agents’ varying levels of social dependencies, mobility, and their groups’ density on their individual and shared goal achievement is analysed.

Taxi-sharing is an emergent transport mode, which has shown promising results economically, by splitting the travel cost between passengers and environmentally, by serving more people in each trip. Intelligent taxi-dispatch approaches can also manage demand by distributing taxis according to population density in a city. Current approaches to taxi-sharing recommend passengers share a taxi by matching their origin and destination, and taxi-dispatch approaches simply send more taxis to populated areas. However, each passenger may have multiple preferences (e.g., level of convenience, time, cost, and environmental factors), and require a mechanism that offers options considering these preferences. Similarly, taxi drivers may have multiple preferences (e.g., number of hours to work, minimum revenue per day) that need to be considered during a taxi-dispatch planning process. This paper presents a multi-agent collaborative passenger matching and taxi-dispatch model. Passengers and drivers are modeled as autonomous agents having multiple often-conflicting preferences. Passenger agents collaboratively take actions to form a group for a taxi-share, and taxi agents collaborate to achieve a dispatch plan.