# E3-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference

arXiv: https://arxiv.org/abs/2605.27428 · HTML: https://mlsanity.com/paper/2605.27428/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 21 May 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 14 of 14)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [MLPerf Inference Benchmark](https://mlsanity.com/paper/1911.02549/) (2019)
- [Parrot: Efficient Serving of LLM-based Applications with Semantic Variable](https://mlsanity.com/paper/2405.19888/) (2024)
- [BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems](https://mlsanity.com/paper/2401.17644/) (2024)
- [Overview of AI and Communication for 6G Network: Fundamentals, Challenges, and Future Research Opportunities](https://mlsanity.com/paper/2412.14538/) (2024)
- [Hybrid SD: Edge-Cloud Collaborative Inference for Stable Diffusion Models](https://mlsanity.com/paper/2408.06646/) (2024)
- [Towards Wireless Native Big AI Model: The Mission and Approach Differ From Large Language Model](https://mlsanity.com/paper/2412.09041/) (2024)
- [Edge Agentic AI Framework for Autonomous Network Optimisation in O-RAN](https://mlsanity.com/paper/2507.21696/) (2025)
- [Wireless Multi-User Interactive Virtual Reality in Metaverse with Edge-Device Collaborative Computing](https://mlsanity.com/paper/2407.20523/) (2024)
- [Learning Multi-Access Point Coordination in Agentic AI Wi-Fi with Large Language Models](https://mlsanity.com/paper/2511.20719/) (2025)

## Built on by (most cited first, 1 of 1)

- [SoK: Semantic Decision Engines in Network Control Loops](https://mlsanity.com/paper/2610.06425/) (2026)

## Abstract (arXiv)

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 E3-Agent, an executable and evolving agent for edge artificial intelligence generated content (AIGC) resource management. E3-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 E3-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, E3-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.