$E^3$-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bao, Rui, Sun, Yaping, Chen, Zhiyong, Yang, Feng, Tao, Meixia, Li, Nan, Zhang, Wenjun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918524931276800
author Bao, Rui
Sun, Yaping
Chen, Zhiyong
Yang, Feng
Tao, Meixia
Li, Nan
Zhang, Wenjun
author_facet Bao, Rui
Sun, Yaping
Chen, Zhiyong
Yang, Feng
Tao, Meixia
Li, Nan
Zhang, Wenjun
contents Edge deployments of generative inference increasingly face two practical realities: per-device per-model performance is often unknown at deployment time, and it is non-stationary due to user-driven semantic events, background load, and device churn. Consequently, a resource manager that is tuned offline under a fixed regime can become brittle and expensive to maintain. This paper presents $E^3$-Agent, an executable and evolving agent for edge artificial intelligence generated content (AIGC) resource management. $E^3$-Agent separates a fast-path router that makes millisecond-level dispatch decisions from a slow-path, event-driven large language model (LLM) meta-controller that mitigates regime shifts through a small, explicit control surface exposed via a tool interface, including risk gating, router configuration, and rapid performance calibration. The agent learns online from execution feedback and continuously adapts to unknown and time-varying service-time mappings. We evaluate $E^3$-Agent in a discrete-event simulator driven by MLPerf-derived device-model measurement priors, covering cold-start warmup and three dynamic regimes: semantic dynamics, device churn, and hidden drift. Across the dynamic scenarios, $E^3$-Agent reduces average latency by 65%-73% compared to the best static baseline, stays within 7%-10% of an online full-information Oracle used for evaluation, and effectively suppresses stutter rate under semantic degradation.
format Preprint
id arxiv_https___arxiv_org_abs_2605_27428
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle $E^3$-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference
Bao, Rui
Sun, Yaping
Chen, Zhiyong
Yang, Feng
Tao, Meixia
Li, Nan
Zhang, Wenjun
Machine Learning
Edge deployments of generative inference increasingly face two practical realities: per-device per-model performance is often unknown at deployment time, and it is non-stationary due to user-driven semantic events, background load, and device churn. Consequently, a resource manager that is tuned offline under a fixed regime can become brittle and expensive to maintain. This paper presents $E^3$-Agent, an executable and evolving agent for edge artificial intelligence generated content (AIGC) resource management. $E^3$-Agent separates a fast-path router that makes millisecond-level dispatch decisions from a slow-path, event-driven large language model (LLM) meta-controller that mitigates regime shifts through a small, explicit control surface exposed via a tool interface, including risk gating, router configuration, and rapid performance calibration. The agent learns online from execution feedback and continuously adapts to unknown and time-varying service-time mappings. We evaluate $E^3$-Agent in a discrete-event simulator driven by MLPerf-derived device-model measurement priors, covering cold-start warmup and three dynamic regimes: semantic dynamics, device churn, and hidden drift. Across the dynamic scenarios, $E^3$-Agent reduces average latency by 65%-73% compared to the best static baseline, stays within 7%-10% of an online full-information Oracle used for evaluation, and effectively suppresses stutter rate under semantic degradation.
title $E^3$-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference
topic Machine Learning
url https://arxiv.org/abs/2605.27428