ARIADNE: Agnostic Routing for Inference-time Adapter DyNamic sElection

2026-06-17

AI Summary

This work addresses the challenge of automatically selecting the optimal parameter-efficient fine-tuning (PEFT) adapter during inference in the absence of task labels. The authors propose a training-free, adapter-agnostic dynamic routing framework that selects adapters at inference time by measuring the distance between the input embedding and the centroid of each adapter’s training data in the latent space. This approach establishes the first universal routing mechanism that requires neither access to internal adapter parameters nor any additional training, offering strong scalability and portability across arbitrary PEFT methods. Experimental results demonstrate that on Llama-3.2-1B-Instruct, the method recovers 97.44% of the oracle performance across 23 NLP tasks and achieves an average selection accuracy of 89.7% when scaled to 44 tasks.

Abstract

The increasing deployment of parameter-efficient fine-tuning (PEFT) has led to model ecosystems in which a single backbone is paired with many task-specialized adapters. In this setting, inference-time queries often arrive without task labels, requiring the system to automatically select the most appropriate adapter from a growing and heterogeneous adapter pool. Existing routing methods either depend on access to adapter internals, such as weight decompositions or gradient-based statistics, or require additional router training, which limits scalability and portability as new adapters are added. We introduce ARIADNE, a training-free, adapter-agnostic routing framework for dynamic adapter selection at inference time. ARIADNE represents each adapter through a set of centroids computed from embeddings of its training set, capturing the data distribution associated with that adapter. Given an unlabeled input, it selects an adapter by measuring proximity to these centroids in latent space. Because routing is performed entirely in the input embedding space, ARIADNE is compatible with arbitrary PEFT methods and requires no modification to the adapters or training procedures. Primarily evaluated with Llama 3.2 1B Instruct on 23 diverse NLP tasks, ARIADNE recovers 97.44% of the upper bound performance. Scaling to 44 tasks, it achieves 89.7% average selection accuracy, without additional training or access to adapter internals.

Problem

• adapter selection
• parameter-efficient fine-tuning
• inference-time routing
• task-agnostic inference
• model ecosystem

Innovation

• adapter routing
• parameter-efficient fine-tuning
• training-free selection
• embedding centroids
• inference-time adaptation