# ORXE: Orchestrating Experts for Dynamically Configurable Efficiency

Source: [ORXE: Orchestrating Experts for Dynamically Configurable Efficiency](<https://www.sota2.com/research/paper/68fa787b1e209131cea78a15>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:16.310Z

Authors: Qingyuan Wang, Guoxin Wang, Barry Cardiff, Deepu John

Published: 2025-05-07T23:16:56.000Z

## Abstract

This paper presents ORXE, a modular and adaptable framework for achieving real-time configurable efficiency in AI models. By leveraging a collection of pre-trained experts with diverse computational costs and performance levels, ORXE dynamically adjusts inference pathways based on the complexity of input samples. Unlike conventional approaches that require complex metamodel training, ORXE achieves high efficiency and flexibility without complicating the development process. The proposed system utilizes a confidence-based gating mechanism to allocate appropriate computational resources for each input. ORXE also supports adjustments to the preference between inference cost and prediction performance across a wide range during runtime. We implemented a training-free ORXE system for image classification tasks, evaluating its efficiency and accuracy across various devices. The results demonstrate that ORXE achieves superior performance compared to individual experts and other dynamic models in most cases. This approach can be extended to other applications, providing a scalable solution for diverse real-world deployment scenarios.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.04850>)

[PDF](<https://arxiv.org/pdf/2505.04850.pdf>)
