2026· IEEE Transactions on Machine Learning in Communications and Networking· Vol 4, pp. 1138-1157· 0 citations· 54 references
Abstract
Orchestrating services across heterogeneous 6G edge-cloud infrastructures requires autonomous coordination systems managing distributed computational resources while satisfying Quality-of-Service (QoS) requirements. Recent advances in Large Language Models (LLMs) enable development of autonomous agents capable of complex reasoning and decision-making for such orchestration tasks. However, applying generic agentic AI frameworks from the machine learning literature to orchestration domains introduces reliability limitations, as trial-and-error decision patterns are unsuitable for environments where errors disrupt services. This work presents AgentEdge, a novel distributed intelligence framework that implements specialized autonomous agents in four orchestration roles: intent processing, infrastructure monitoring, strategic planning, and action execution. AgentEdge introduces the PARES (Perceive, Act, Reason, Evaluate, Sustain) framework establishing minimum capabilities required for autonomous agent qualification. Central to AgentEdge is the ActSimCrit (Action-Simulation-Critic) planning methodology, which validates orchestration plans through digital twin simulation before execution, eliminating direct infrastructure experimentation risks. Agents coordinate multi-step operations and adapt strategies based on constraint feedback. Structured outputs constrain agent decision spaces to feasible orchestration actions while preserving optimization flexibility. Experimental evaluation in six orchestration scenarios validates AgentEdge through comparison with baseline agentic frameworks and ablation studies. AgentEdge achieves $2.76\times $ higher success rate compared to generic agentic frameworks (ReAct, LATS) and $10\times $ reduction in API call variability. The core ActSimCrit digital twin component alone contributes $1.47\times $ success improvement when compared to direct planning without simulation. AgentEdge achieves significant power savings across infrastructure scales from 8 to 35 nodes.
Cloud-edge computing environments are evolving rapidly, requiring orchestration mechanisms that may automatically construct and manage complex multi-step workflows with little human intervention. We introduce a framework for the agentic AI and how it should be able to orchestrate an autonomous end-to-end workload of cloud-edge enterprise infrastructures in general. The proposed framework relies on large language model (LLM)-driven agents capable of dynamic task decomposition, real-time decision-making, and self-correcting execution pipelines to manage heterogeneous workloads. Through the incorporation of multi-agent coordination protocols, context-aware scheduling algorithms, and feedback-driven optimization loops, the system facilitates seamless task delegation throughout edge nodes and cloud backend systems while managing latency, resource allocation, and compliance constraints. Experimental evaluations show up to percentage improvements in workflow completion rates, resource utilization, and fault tolerance over traditional static-command Rule-based orchestration approaches. Additionally, the framework features explainability modules and audit trails to promote transparency and accountability in autonomous operations. The results provide evidence that agentic AI architectures can serve as a scalable, resilient and intelligent control mechanism for next generation enterprise workflow management across hybrid cloud-edge settings. This has laid a foundation and is to our best of knowledge, the first systematic pioneers work that lays down a roadmap for production-grade autonomous orchestration deployed in analytics and enterprise domains.
Shiza Arshad, Anusha Joodala, A. Agade et al.· 2026 International Conferenc...· 0 citations
The main conclusion is that practical Agentic IoT depends less on placing an entire agent at one tier than on partitioning perception, memory, reasoning, and action under explicit latency, privacy, reliability, and safety constraints.
Experimentation on distributed, heterogeneous computing environments—from edge devices to large-scale cloud platforms—demands orchestration technologies that are both flexible and extensible. Kiso is an open-source framework designed to provision resources and manage complex scientific workflows across the edge-to-cloud continuum. Its architecture unifies infrastructure provisioning, experiment configuration, and reproducible execution, enabling researchers to compose and monitor experiments that span geographically dispersed sites and variable network conditions. Although Kiso was conceived for workflow management—coordinating data-intensive tasks and ensuring reproducibility across dynamic infrastructures—its modular design makes it equally promising for providing reproducible environments for deploying and studying emerging agentic frameworks, where autonomous AI agents require consistent resource provisioning, cross-site communication, and result collection. We describe Kiso’s core capabilities for resource orchestration, experiment lifecycle management, and integration with containerized services, and we outline how these capabilities can support distributed multi-agent systems. In particular, we discuss how its declarative provisioning, extensible task abstractions, and built-in monitoring and output collection provide a natural foundation for experiments in which reasoning agents plan, negotiate, and adapt in real time. This study situates Kiso at the intersection of scientific workflow management and complex, agent-based computing, highlighting its potential to accelerate research on adaptive, self-organizing cyber-physical systems—an emerging frontier in complex systems science.
R. Mayani, K. Vahi, M. Rynge et al.· Frontiers in Complex Systems· 1 citation
The rapid advancement of artificial intelligence is driving a fundamental transformation in enterprise
computing, shifting from traditional software-as-a-service (SaaS) models to agent-as-a-service (AaaS) paradigms powered
by autonomous, goal-driven systems. Although large language models (LLMs) have significantly enhanced reasoning and
content generation capabilities, their effective adoption in enterprise environments requires scalable orchestration, cost
efficiency, and seamless integration with complex workflows. This paper introduces UMA, a Unified Multi-Agent
Framework for enterprise AI systems, designed to support the complete lifecycle of agentic systems, including deployment,
orchestration, execution, monitoring, and return-on-investment (ROI) realization. The proposed framework integrates
multi-agent coordination, tool orchestration, memory management, and adaptive decision-making within a layered
architecture that enables scalable and efficient enterprise operation.
Through an analysis of enterprise use cases and real-world system implementations, it is demonstrated that agentbased systems can autonomously execute complex tasks, reduce human workload, and improve operational efficiency
across business functions. Furthermore, a performance and economic model is presented to quantify the trade-offs
between cost, scalability, and autonomy in enterprise AI deployments. The findings highlight the transformative potential
of UMA in enabling scalable, efficient, and intelligent enterprise systems, positioning agent-as-a-service as a foundational
paradigm for the next generation of enterprise computing.
Umamaheswara Rao Kukkala· International Journal of Inn...· 0 citations
A semantic-uncertainty-guided orchestration approach, HASSUM is introduced as a general framework for uncertainty-aware coordination in multi-agent systems and suggests that semantic uncertainty is a practical and general-purpose signal for improving robustness and trustworthiness in agentic AI systems.
John Knowlton, Aritra Guha, Risto Miikkulainen· 0 citations
Agentic systems have emerged as a promising paradigm for solving complex tasks by coordinating specialized LLM-based agents. However, most existing systems primarily optimize task success while giving limited consideration to execution efficiency under practical constraints such as executor capability and computational cost. Existing router-based methods have limited ability to reason over rich, evolving task contexts, multi-step dependencies, and intermediate execution feedback, and often generalize poorly to unseen executors. We propose EASy, a trainable agentic framework that jointly optimizes task performance and computational efficiency through reinforcement learning. EASy equips an LLM-based orchestrator with explicit knowledge of the capability and cost profiles of heterogeneous executors, enabling context-sensitive coordination beyond performance-only routing. It further introduces a milestone-plan-act workflow that decomposes complex tasks into manageable milestones, constructs dependency-aware execution graphs, assigns suitable executors, and parallelizes independent steps while adapting subsequent decisions to intermediate outcomes. To train the orchestrator, we develop a tree-structured rollout procedure that explores alternative milestone decompositions and execution plans, together with multi-component rewards that capture task correctness, execution efficiency, and trajectory completeness. Extensive experiments on mathematical reasoning, embodied decision-making, and deep research benchmarks show that EASy consistently achieves stronger performance-efficiency trade-offs than strong agentic baselines.
Junnan Liu, Linhao Luo, Thuy-Trang Vu et al.· 0 citations