EdgeCraft: Automated Model Crafting for Edge IoT

2026-09-28

AI Summary

This work addresses the fragmented development pipelines and the difficulty of jointly optimizing quality, latency, and energy consumption in edge IoT model development. We propose an LLM-driven end-to-end automation framework that directly translates high-level user intents into deployable edge ML artifacts. Core innovations include a constraint-aware synthesis tree to guide search space optimization, a multi-fidelity verifier to reduce on-device validation overhead, and a parallelized architecture that isolates cloud-based training from device-side verification. Evaluated across 50 public tasks, the proposed framework surpasses baseline performance on 40 tasks and satisfies service level objectives (SLOs) on 45. Furthermore, it demonstrates strong generalization capabilities on a proprietary dataset collected in-house.

Abstract

Machine learning (ML) increasingly powers Internet of Things (IoT) applications at the edge. Yet producing a deployable edge ML artifact for a specific scenario requires navigating a huge search space spanning data representation, model design, training on domain-specific data, and runtime customization. This workflow is fragmented and difficult to scale across diverse edge applications. We present EdgeCraft, an LLM-driven system that turns high-level intent into deployable edge ML artifacts. Building such a system raises two challenges: (1) How can an LLM be guided to find high-quality solutions that meet dynamic SLOs for task quality, latency, and energy? (2) How can trustworthy target-device verification be obtained at low cost? EdgeCraft addresses these challenges with two designs. (1) A constraint-aware synthesis tree explores alternative candidates and uses measured SLO gaps to guide each improvement. (2) A multi-fidelity verifier progressively combines low-cost checks with full target-device verification to reduce verification cost while preserving reliable verification results. It also records verified failures for reuse, avoiding repeated device work. To support concurrency, EdgeCraft provides a multi-tenant runtime that runs cloud training and target-device verification in parallel while isolating requests. Across 50 public tasks, EdgeCraft exceeds the task-specific Reference in best-observed quality on 40 tasks and finds an SLO-feasible artifact on 45, with the two outcomes overlapping on 38 tasks. Moreover, EdgeCraft achieves competitive performance on our self-collected SEN dataset, suggesting its generalizability to real-world IoT sensing tasks.

Problem

• Edge IoT
• Automated ML
• SLO constraints
• Model deployment
• Device verification

Innovation

• LLM-driven system
• Edge IoT
• Constraint-aware synthesis tree
• Multi-fidelity verifier
• Automated model crafting