Albert Y. Zomaya

SpecBox: Speculative Sandbox Scheduling for Efficient LLM Agent Serving

This work presents SpecBox, a runtime built around speculative sandbox preallocation tailored for dynamic LLM agent execution pipelines, and implements keyword matching and streaming semantic embedding to enable intent-driven sandbox prewarming, which identifies pending tool execution demands mid-LLM token generation a...

MultiSecDFL: Multi-Metric Filtering-Based Secure Aggregation Method for Decentralized Federated Learning

Agentic Service-Oriented Computing: A Manifesto for the Next Frontier of Service-Oriented Computing

It is argued that the Services Computing community is especially well positioned to provide the conceptual and engineering spine for this emerging field, transforming agentic AI from fragmented demonstrations into dependable, service-based systems worthy of human and organisational trust.

ElastiCo: Elastic Configuration and Interference-Aware Orchestration for GPU Clusters

ElastiCo is presented, an elastic co-location framework that enables training and inference workloads to safely share GPUs through three integrated mechanisms that decomposes the resulting multi-resource allocation problem into per-job configuration selection subproblems via dynamic per-resource shadow prices.