Intent-Aware Predictive Orchestration for Softwarized Networks Using LLM-Assisted Policy Translation

Dependency-Aware Reliable Orchestration for Smart-IoT Control with Reasoning-Aligned LLMs

Large Language Models (LLMs) offer a natural interface for smart-IoT control, yet reliable deployment requires more than producing valid API calls. Multi-device commands often contain preconditions, ordering constraints, and conflicts that must be satisfied before actions are safely executed. This paper presents DARIO, a dependency-aware orchestration framework for translating natural-language commands into verified IoT action plans. DARIO combines supervised instruction tuning, KL-regularized PPO, an explicit dependency graph $\mathcal{G}=(V, E)$, and a lightweight verifier that checks schema, execution, dependency, and safety constraints before commit. Verifier outcomes are folded into a decomposed reward, enabling the policy to learn from dependency violations rather than treating plans as flat token sequences. On a 2k-prompt held-out HA-Instruct split across five seeds, DARIO achieves $0.85 \pm 0.01$ JSON exact match, perfect schema validity, $0.91 \pm 0.01$ overall task success, and $0.81 \pm 0.02$ success on the dependency-heavy L3 split, outperforming SIT and SIT+PPO baselines by large margins. It also raises dependency satisfaction to 0.94, reduces unsafe execution to 0.02, and runs as a 4-bit 8B LoRA deployment at about 609 ms including verification.

Utility-Guided Orchestration for Cost-Efficient Tool-Augmented LLM Services

Tool-augmented large language model (LLM) services can solve complex tasks through retrieval and external tools, but current execution paradigms often trade adaptability for efficiency. Fixed workflows are predictable but rigid, while freeform reasoning loops such as ReAct may over-execute and issue redundant tool calls. We propose a lightweight utility-guided orchestration framework that formulates agent control as a costaware sequential decision problem over a compact action space: respond, retrieve, tool call, verify, and stop. An interpretable utility function balances expected gain, step-cost proxies, uncertainty, and redundancy. Experiments on multi-hop question answering show that the policy offers a controllable quality-cost trade-off and reduces token consumption by up to 10.6% in the semantic-redundancy setting while preserving similar answer quality. The framework is intended as an inspectable control layer for practical LLM services rather than a universally dominant accuracy optimizer.

A Hybrid Approach for Intent-Driven Recommendation of CEI Orchestration Frameworks

HGT-Autoscaler: Dependency-Aware Proactive Scaling of Microservices Using Heterogeneous Graph Transformers

Autoscaling of microservice applications in containerized cloud environments remains a challenging problem due to complex inter-service dependencies, hierarchical deployment structures, and highly dynamic workloads. Existing autoscaling approaches are predominantly reactive or rely on homogeneous representations of system interactions, which limits their ability to anticipate load propagation across heterogeneous components such as services, message queues, and infrastructure layers. In this paper, we propose HGT-Autoscaler, a dependency-aware proactive autoscaling framework based on Heterogeneous Graph Transformers. The system is modeled as a multi-relational hierarchical graph that explicitly captures both service-level interactions and deployment structure across containers, virtual machines, and physical nodes. The proposed model leverages relation-aware attention mechanisms to learn expressive system representations and forecast resource requirements in a proactive manner. The autoscaling problem is formulated as a constrained optimization task that minimizes average response time under a given cost budget. Experimental evaluation on realistic microservice workloads demonstrates that the proposed approach significantly reduces latency and improves scaling stability compared to reactive and learning-based baselines, while maintaining cost efficiency.

A Collaborative Edge Intelligence Framework for SFC Provisioning via Language Models

As Software-Defined Networking (SDN) and Network Function Virtualization (NFV) enabled networks scale in size and complexity, monitoring and managing Service Function Chains (SFCs) under stringent latency and resource constraints becomes increasingly challenging. Although Deep Reinforcement Learning (DRL) is widely applied to SFC provisioning and Virtual Network Function (VNF) placement, enhanced network state monitoring is crucial to capture unexpected network conditions and guide DRL agents toward more adaptive decisions. In this context, Language Models (LMs) enable flexible, natural-language (NL)–based, query-driven network monitoring; however, directly processing complex multi-metric NL queries is computationally expensive and error-prone. This paper proposes an end-to-end (E2E) edge-based query translation pipeline that decomposes multi-metric NL queries into simpler single-metric sub-queries. Query decomposition is performed using a retrieval-augmented language model (RAG-LLM) and compared with a lightweight rule-based decomposition baseline. The resulting sub-queries are translated into Structured Query Language (SQL) using FLAN-T5. A cloud-only baseline, which directly translates NL queries to SQL without decomposition, is also evaluated. The results show that the rule-based edge pipeline achieves the lowest latency, reducing E2E latency by up to 78% compared to RAG-LLM and 18% compared to cloud execution under high workloads. Under increasing arrival rates for the largest workload, the rule-based edge pipeline maintains superior performance over cloud, reducing total E2E latency by 57% at $\lambda = 0.8$ . While RAG-LLM provides greater flexibility for unseen query patterns, both edge-based approaches achieve 100% NL2SQL accuracy with zero decomposition failures, outperforming the cloud-only baseline (95% accuracy).

LMEdge: QoS-Aware LLM Inference Orchestration on Edge Clusters

This paper employs five lightweight machine learning models to predict query-specific latency, accuracy, resource usage, and response size for each model-size-quantization-device combination, and design a lightweight heuristic that approximates the BILP solution.