$E^3$-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference
This paper presents $E^3$-Agent, an executable and evolving agent for resource management of edge AIGC. It separates a fast-path router from a slow-path LLM meta-controller, learns online from execution feedback, and adapts to unknown time-varying service-time mappings. Evaluation shows 65%-73% latency reduction over static baselines and effective stutter suppression.
Article intelligence
Key points
- Edge generative inference faces unknown per-device performance and non-stationarity.
- $E^3$-Agent uses a dual-path architecture: fast router + slow LLM meta-controller.
- Learns online from execution feedback, continuously adapting to dynamic regimes.
- Reduces average latency by 65%-73% compared to the best static baseline.
Why it matters
This matters because edge generative inference faces unknown per-device performance and non-stationarity.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.27428] $E^3$-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference
[Submitted on 21 May 2026]
Title:$E^3$-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference
View a PDF of the paper titled $E^3$-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference, by Rui Bao and 6 other authors
View PDF HTML (experimental)
Abstract: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.
Comments: 13 pages, 4 figures, 6 tables
Subjects:
Machine Learning (cs.LG)
Cite as: arXiv:2605.27428 [cs.LG]
(or arXiv:2605.27428v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.27428
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Rui Bao [view email] [v1] Thu, 21 May 2026 12:32:43 UTC (803 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled $E^3$-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference, by Rui Bao and 6 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-05
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
IArxiv recommender toggle
IArxiv Recommender (What is IArxiv?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)