arXiv:2603. 20895v3 Announce Type: replace-cross Abstract: Existing routers rely on semantic query features or handcrafted features, which often fail to capture model-specific failures or intrinsic task difficulty.
arXiv:2603. 24787v2 Announce Type: replace Abstract: Routing has emerged as a promising strategy for balancing performance and cost in large language model (LLM) systems that combine lightweight models with powerful but expensive large models.
arXiv:2609.22884v1 Announce Type: new Abstract: Long-context inference has become a defining capability of large language models, but exact dense attention remains costly due to its quadratic scaling...
arXiv:2604. 00421v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) layers increase model capacity by activating only a small subset of experts per token, and typically rely on a learned router to map hidden states to expert assignments.
arXiv:2606. 07587v1 Announce Type: new Abstract: LLM routing has become a popular approach to improve the cost-quality trade-off of LLM services by dynamically selecting a model for each query.
RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing proposes the Superposed Specialisation Hypothesis (SSH), suggesting that experts in Sparse Mixture of Experts models specialise in a disjoint union of fine‑grained features rather than a single domain. The paper introduces RouterInterp, a method that identifies Sparse Autoencoder features predictive of routing decisions and generates unified natural‑language explanations. On the gpt‑oss‑20b model, RouterInterp achieves approximately 65% higher detection accuracy than previous token‑statistics based methods, offering a scalable way to explain expert routing.
arXiv:2609.15131v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) require substantial computation to process numerous visual tokens across all transformer layers. Most method...
arXiv:2606. 19079v2 Announce Type: replace Abstract: Parameter-efficient fine-tuning (PEFT) has led to model ecosystems in which a single backbone is paired with many task-specialized adapters.
arXiv:2609.37362v1 Announce Type: new Abstract: Large language model (LLM) routing aims to assign each query to the most suitable model from a heterogeneous candidate pool, improving the quality--eff...
The paper introduces Voyager, a lightweight router that learns to select a sparse, final‑layer‑anchored expert from CLIP’s layer depth for out‑of‑distribution (OOD) detection. Using a weak OOD supervision context, Voyager outperforms state‑of‑the‑art prompt‑learning methods on three benchmarks, achieving an average FPR@95 of 18.86 on ImageNet‑1K. The router can be trained in about two minutes with less than 1 GB of memory, making it roughly 20× more efficient than existing approaches.
The paper introduces SCX Router, a lightweight GLiClass-based model selector that assigns suitability scores to inference-time language models without autoregressive generation. It uses a 0.6B-parameter Qwen3 decoder with a shallow bidirectional scorer, preserving a text-only key–value cache across sessions and predicting task attributes such as type, difficulty, and expected output length. The authors build a comprehensive task ontology with 23 families, 115 types, and 1,173 synthetic examples, generating 150,000 verifier-scored tasks to train the router, which outperforms baseline models on LiveBench subsets with a top‑1 score of 0.707 versus 0.696 for the strongest fixed model.
arXiv:2610.19705v1 Announce Type: new Abstract: LLM routing dynamically selects and coordinates heterogeneous language models across diverse tasks. However, existing approaches are largely built arou...