paper-with-me

Papers

Continual Model Routing in Evolving Model Hubs

2026-05-27 · Jack Bell, Giacomo Carfì, Gerlando Gramaglia, Vincenzo Lomonaco arxiv

AI model hubs provide access to a rapidly growing collection of powerful pre-trained models, enabling off-the-shelf mixture-of-experts systems with different routing strategies. However, this rapid growth poses two fundamental challenges: scaling model selection across thousands of experts and continually updating routing mechanisms as new models and tasks are introduced. In this paper, we formalise this setting as Continual Model Routing (CMR) and propose CMRBench, a new large-scale benchmark simulating realistic hub expansion and including over 2,000 candidate models. Finally, we introduce CARvE, a contrastive embedding approach for efficient continual model routing via checkpoint-based anchoring and structured replay. Extensive empirical results and ablations show that CARvE significantly outperforms zero-shot retrieval, fine-tuning, and adapter-merging baselines in model, family, and domain-level accuracy.

📄 PDF Abstract BibTeX arXiv:2605.28577

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents

2026-09-16 · Jiaxuan Jiang, Liyuan He, Zhixuan Fang hf

Current Mixture-of-Agents (MoA) paradigms generally treat query routing and agent fine-tuning as separate processes, limiting their ability to respond to evolving agent capabilities. This disconnect prevents routing stra…

Reinforcement Learning

Is Our Benchmark Enough? An Analysis of Continual Learning for MLLMs

2026-06-18 · Van-Tuan Tran, Shruthi Gowda, Merim Dzaferagic, Marco Ruffini arxiv

Continual adaptation is essential for multimodal large language models (MLLMs) deployed across evolving domains, but the state-of-the-art MR-LoRA method highly relies on the assumption that a MLLM-based router is necessa…

Continual Learning

MixLLM: Dynamic Routing in Mixed Large Language Models

2025-02-09 · Xinyuan Wang, Yanchi Liu, Wei Cheng, Xujiang Zhao 외

Large Language Models (LLMs) exhibit potential artificial generic intelligence recently, however, their usage is costly with high response latency. Given mixed LLMs with their own strengths and weaknesses, LLM routing ai…

Continual Learning

FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning

2026-02-02 · Hongwei Yan, Guanglong Sun, Kanglei Zhou, Qian Li 외 arxiv

General continual learning (GCL) challenges intelligent systems to learn from single-pass, non-stationary data streams without clear task boundaries. While recent advances in continual parameter-efficient tuning (PET) of…

Continual Learning

HubRouter: Learning Global Routing via Hub Generation and Pin-hub Connection

2023-09-21 · NeurIPS 2023 11

Global Routing (GR) is a core yet time-consuming task in VLSI systems. It recently attracted efforts from the machine learning community, especially generative models, but they suffer from the non-connectivity of generat…