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

DevFeed: [A Self-Exploring and Self-Evolving Paradigm for Adaptive Edge AI Development](<https://devfeed.tech/articles/a-self-exploring-and-self-evolving-paradigm-for-adaptive-edge-ai-development-113507.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.01377>)

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

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-systems](<https://devfeed.tech/tags/agentic-systems.md>), [agentic-workflow](<https://devfeed.tech/tags/agentic-workflow.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-application-development](<https://devfeed.tech/tags/ai-application-development.md>), [ai-development](<https://devfeed.tech/tags/ai-development.md>), [automate](<https://devfeed.tech/tags/automate.md>), [code](<https://devfeed.tech/tags/code.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [development](<https://devfeed.tech/tags/development.md>), [edge](<https://devfeed.tech/tags/edge.md>), [edge-ai](<https://devfeed.tech/tags/edge-ai.md>), [edge-ai-development](<https://devfeed.tech/tags/edge-ai-development.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [explore](<https://devfeed.tech/tags/explore.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>)

## AI overview

SE2 lets agents adapt their workflow for edge AI development by choosing among four operations--retrieve, reason, code, and test--based on context, rather than following a fixed sequence. The abstract reports that synthesized programs achieved up to 26% higher accuracy and used 28% fewer resources than state-of-the-art baselines, while showing greater adaptability to unforeseen scenarios. The supplied material is an abstract, so it does not describe evaluation details or limitations.

## Source excerpt

arXiv:2611.01377v1 Announce Type: cross 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.