Metraipolis › archive › dc_8dfd9092a471
AgentDP: Towards Automated Model Deployment for Heterogeneous Embedded AI Applications — arXiv:2610.30760
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.30760
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-23T15:13:02.003Z
- SHA-256 of the archived text
8a460a483b666c5c4310d442173c6ec01516a83b07cb1bd7447953660d03cd0d- Stable URL of this page
https://metraipolis.com/documento/dc_8dfd9092a471
How to cite
AgentDP: Towards Automated Model Deployment for Heterogeneous Embedded AI Applications — arXiv:2610.30760 — arXiv (en), https://arxiv.org/abs/2610.30760 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8dfd9092a471 (Metraipolis archive dc_8dfd9092a471, sha256 8a460a483b666c5c4310d442173c6ec01516a83b07cb1bd7447953660d03cd0d)
BibTeX
@misc{dc8dfd9092a471,
title = {AgentDP: Towards Automated Model Deployment for Heterogeneous Embedded AI Applications — arXiv:2610.30760},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.30760},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8dfd9092a471; sha256 8a460a483b666c5c4310d442173c6ec01516a83b07cb1bd7447953660d03cd0d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30760. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper presents AgentDP, which aims to deploy pre-trained AI models on heterogeneous embedded devices by fully automating model optimization and adaptation (O&A) with Large Language Model (LLM) agents. AgentDP not only significantly reduces human effort via automation but also enhances model inference efficacy by integrating LLMs with device-specific domain knowledge. To deliver a robust automation framework, AgentDP develops novel solutions to address three key technical challenges: 1) To help users elicit clear requirements, we propose a user requirement standardization module; 2) To mitigate the execution environment mismatch between AI models and heterogeneous embedded devices, we design an operator-aware model partition paradigm that enables different parts of the model to be efficiently executed on distinct inference engines. 3) To avoid re-searching optimization hyperparameters for new tasks, we propose a configuration reuse module that heuristically retrieves previous hyperparameter configurations for efficient reuse. Extensive experiments demonstrate that by fully automating the entire O&A process, AgentDP reduces entire model adaptation time by up to 80% compared with manual O&A while achieving higher task accuracy (more than 13% on average) than the baselines. Additionally, a comprehensive user study also exhibits the robust generalizability of AgentDP in adapting to different user requirements for heterogeneous embedded devices. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.30760 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-23T15:09:08.396Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).