cs.AINov 1, 2026

A Self-Exploring and Self-Evolving Paradigm for Adaptive Edge AI Development

Authors: Leming Shen, Qiang Yang, Xinyu Huang, Zijing Ma, Yuanqing Zheng, Chris Xiaoxuan Lu

Organizations: Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China · Department of Computer Science and Technology, University of Cambridge, Cambridge, UK · Department of Computer Science, University College London, UK

Abstract

Large Language Models (LLMs) exhibit powerful code generation abilities, fostering agentic systems to automate edge AI application development. However, existing agents typically operate via fixed agentic workflows and predefined design spaces, struggling to handle rapidly evolving demands of real-world scenarios (e.g., heterogeneous data modalities, diverse task pipelines). Unlike prior systems that treat LLMs mainly as code generators following rigid workflows, we fully exploit their reasoning capabilities to allow agents to determine their own workflows on the fly. To this end, we propose SE2, a self-exploring and self-evolving paradigm for adaptive edge AI development. Inspired by human learning processes, we distill development into four atomic operations (retrieve, reason, code, test), and empower agents to explore workflows by dynamically and adaptively selecting an appropriate next operation based on the current context. Extensive evaluations show that, with adaptive workflows, the synthesized programs achieve up to 26% higher accuracy and consume 28% lower resources than state-of-the-art baselines, while maintaining superior adaptability to unforeseen edge AI scenarios. This highlights the potential of reasoning-driven adaptive agentic workflow in edge AI development.

Figures & tables

Explore similar work

CardsList
  1. A Self-Calibrating Agentic AI Framework for Autonomous Edge Resource Allocation

    Jul 24, 2026Fin Gentzen, Marla Grunewald, Iulisloi Zacarias +2Edge ComputingLanguage Model Calibration

  2. AgentWare: Automating the Lifecycle of Agentic Applications across the Edge-to-Cloud Continuum

    Sep 28, 2026Michalis Kasioulis, Moysis Symeonides, George Pallis +1LLM Agent OrchestrationLLM Agent Evaluation

  3. Position Paper: From Edge AI to Adaptive Edge AI

    Mar 31, 2026Fabrizio Pittorino, Manuel RoveriEdge AIAdaptive Inference