Related papers: SkillOrchestra: Learning to Route Agents via Skill…
As artificial intelligence engineering paradigms shift from single-agent Prompt and Context Engineering toward multi-agent \textbf{Coordination Engineering}, the ability to codify and systematically improve how multiple agents collaborate…
Service-based architectures provide substantial benefits, yet service orchestration remains a challenge, particularly for newcomers. While various resources on orchestration techniques exist, they often lack clarity and standardization,…
The inherent capabilities of a language model (LM) and the reasoning strategies it employs jointly determine its performance in reasoning tasks. While test-time scaling is regarded as an effective approach to tackling complex reasoning…
Synthesizing unstructured research materials into manuscripts is an essential yet under-explored challenge in AI-driven scientific discovery. Existing autonomous writers are rigidly coupled to specific experimental pipelines, and produce…
Cloud computing allows scalable resource provisioning, but dynamic workload changes often lead to higher costs due to over-provisioning. Machine learning (ML) approaches, such as Long Short-Term Memory (LSTM) networks, are effective for…
The emergence of multi-agent systems powered by large language models (LLMs) has unlocked new frontiers in complex task-solving, enabling diverse agents to integrate unique expertise, collaborate flexibly, and address challenges…
rApps and xApps need to be controlled and orchestrated well in the open radio access network (O-RAN) so that they can deliver a guaranteed network performance in a complex multi-vendor environment. This paper proposes a novel intent-driven…
Managing disruptions in railway traffic management is a major challenge. Rising traffic density and infrastructure limits increase complexity, making the Vehicle Routing and Scheduling Problem (VRSP) difficult to solve reliably and in real…
Online matching problems arise in many complex systems, from cloud services and online marketplaces to organ exchange networks, where timely, principled decisions are critical for maintaining high system performance. Traditional heuristics…
Interference among concurrent transmissions in a wireless network is a key factor limiting the system performance. One way to alleviate this problem is to manage the radio resources in order to maximize either the average or the worst-case…
Large language model (LLM) agents increasingly rely on reusable skills: capability packages that combine instructions, control flow, constraints, and tool calls. In current agent systems, however, skills are still represented by text-heavy…
Agentic AI systems that invoke external tools are powerful but costly, leading developers to default to large models and overspend inference budgets. Model routing can mitigate this, but existing routers are designed for chat completion…
Large language models (LLMs) exhibit impressive capabilities across a wide range of tasks, yet the choice of which model to use often involves a trade-off between performance and cost. More powerful models, though effective, come with…
Software-Defined Networking enables the centralized orchestration of data traffic within a network. However, proposed solutions require a high degree of architectural penetration. The present study targets the orchestration of network…
Agent skills today are static artifact: authored once -- by human curation or one-shot generation from parametric knowledge -- and then consumed unchanged, with no mechanism to improve from real use. We propose \textbf{SkillEvolver}, a…
Due to the highly variable execution context in which edge services run, adapting their behavior to the execution context is crucial to comply with their requirements. However, adapting service behavior is a challenging task because it is…
Research on robotic manipulation has developed a diverse set of policy paradigms, including vision-language-action (VLA) models, vision-action (VA) policies, and code-based compositional approaches. Concrete policies typically attain high…
AI tasks differ in complexity and are best addressed with different computation strategies (e.g., combinations of models and decoding methods). Hence, an effective routing system that maps tasks to the appropriate strategies is crucial.…
Orchestrating service-oriented workflows is typically based on a design model that routes both data and control through a single point - the centralised workflow engine. This causes scalability problems that include the unnecessary…
Vast quantities of compute (GPU cycles on personal workstations, idle inference servers, and edge devices between jobs) go unused because no incentive-aligned protocol exists for their owners to share them safely and profitably. Existing…