IR3DE: A Linear Router for Large Language Models
Summary
IR3DE is a ridge regression-based router that selects domain-expert LLMs for different tasks, achieving competitive performance while enabling dynamic addition or removal of experts without retraining.
View Cached Full Text
Cached at: 06/10/26, 09:43 AM
Paper page - IR3DE: A Linear Router for Large Language Models
Source: https://huggingface.co/papers/2606.06098
Abstract
A ridge regression-based routing method achieves competitive performance in selecting domain-expert LLMs for different tasks while enabling dynamic addition/removal of experts without retraining.
Foundational Large Language Models (LLMs) demonstrate proficiency on a wide range of general tasks, and achieve remarkable results on various specialized tasks viadomain-expert LLMs. With the ever-growing list of available LLMs,inference routersare being proposed to select the most appropriate LLM for each prompt. However, existing routing methods either optimize cost across weak-to-strong generalist LLMs or require substantial training to support domain-expertise routing. In this paper, we propose IR3DE, aRidge Regression-based Router for Domain Experts that provides cheap and fast routing decisions for each prompt. We evaluate IR3DE in twoCausal Language Modeling(CLM) settings where the tasks arenext-token predictionfor all domains, and one reasoning setting where each domain has its own distinct reasoning task. Despite being alinear router, IR3DE achieves performance comparable to the other baselines in both CLM settings, and surpassing them in the reasoning setting, with a normalized performance of 98.4%. Moreover, IR3DE enables the addition or removal of new domain experts without requiring the router to be retrained from scratch, allowing a dynamic set of LLMs to be served with minimal disruption to the router itself. Our code is available at: github.com/gensyn-ai/IR3DE.
View arXiv pageView PDFProject pageGitHub2Add to collection
Get this paper in your agent:
hf papers read 2606\.06098
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2606.06098 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2606.06098 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2606.06098 in a Space README.md to link it from this page.
Collections including this paper1
Similar Articles
LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers
LLMRouter presents a unified formulation of LLM routing as a sequential decision process, along with an open-source infrastructure and benchmark (xRouteBench) for developing, evaluating, and deploying LLM routers. Empirical results show learned routers achieve 14.6% relative improvement over the strongest fixed-model baseline.
VDAR-Router: Adaptive LLMs Routing via Verbalized Query Difficulty Analysis Retrieval
A new paper proposes VDAR-Router, a difficulty-aware retrieval-based routing framework for LLMs that adaptively selects models based on query difficulty, achieving better cost-performance trade-offs.
alexzhang13/rlm
Recursive Language Models (RLMs) introduce a task-agnostic inference paradigm enabling language models to handle near-infinite contexts by recursively calling themselves over input, with an accompanying open-source inference engine and training environment.
$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction
R²-dLLM introduces spatio-temporal redundancy reduction techniques that cut diffusion LLM decoding steps by up to 75% while preserving generation quality, addressing a key deployment bottleneck.
TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning
Introduces TSRouter, a graph-based dynamic routing framework that selects the optimal modality (LLM or VLM) and model for time-series reasoning tasks, achieving 16-46% relative improvement over baselines and demonstrating zero-shot generalization.