14 articles mentioning router
arXiv:2604.16401v1 Announce Type: cross Abstract: Graph-based retrieval-augmented generation (GraphRAG) has recently emerged as a powerful paradigm for knowledge-intensive question answering, especially for tasks that require structured evidence organization and multi-hop reasoning. However, existin
arXiv:2604.16883v1 Announce Type: new Abstract: In long-context decoding for LLMs and LMMs, attention becomes increasingly memory-bound because each decoding step must load a large amount of KV-cache data from GPU memory. Existing acceleration strategies often trade efficiency for accuracy by relyin
arXiv:2601.08276v2 Announce Type: replace Abstract: With the rise of the Agent Web and Model Context Protocol (MCP), the agent ecosystem is evolving into an open collaborative network, exponentially increasing accessible tools. However, current architectures face severe scalability and generality bo
arXiv:2604.15499v1 Announce Type: cross Abstract: Cryptographically secure neural network inference typically relies on secure computing techniques such as Secure Multi-Party Computation (MPC), enabling cloud servers to process client inputs without decrypting them. Although prior privacy-preserving
arXiv:2604.16264v1 Announce Type: cross Abstract: Vision Language models (VLMs) have demonstrated strong performance across a wide range of benchmarks, yet they often suffer from modality dominance, where predictions rely disproportionately on a single modality. Prior approaches primarily address th
arXiv:2604.15022v1 Announce Type: cross Abstract: Cost-aware routing dynamically dispatches user queries to models of varying capability to balance performance and inference cost. However, the routing strategy introduces a new security concern that adversaries may manipulate the router to consistent
arXiv:2510.10925v2 Announce Type: replace-cross Abstract: Training student models on synthetic data generated by strong teacher models is a promising way to distilling the capabilities of teachers. However, recent studies show that stronger models are not always optimal teachers, revealing a mismatc
arXiv:2604.09019v1 Announce Type: cross Abstract: Two-hop QA retrieval splits queries into two regimes determined by whether the hop-2 entity is explicitly named in the question (Q-dominant) or only in the bridge passage (B-dominant). We formalize this split with three theorems: (T1) per-query AUC i
arXiv:2604.02319v2 Announce Type: replace Abstract: When posed with prompts that permit a large number of valid answers, comprehensively generating them is the first step towards satisfying a wide range of users. In this paper, we study methods to elicit a comprehensive set of valid responses. To ev
arXiv:2603.21354v2 Announce Type: replace Abstract: Over the past year, the vLLM Semantic Router project has released a series of work spanning: (1) core routing mechanisms -- signal-driven routing, context-length pool routing, router performance engineering, policy conflict detection, low-latency e
arXiv:2604.05149v1 Announce Type: new Abstract: Large language model agents often exhibit complementary strengths, making routing a promising approach for multi-agent question answering. However, existing routing methods remain limited in two important ways: they typically optimize over a fixed pool
arXiv:2604.03455v1 Announce Type: cross Abstract: Retrieval-Augmented Generation pipelines span a wide range of retrieval strategies that differ substantially in token cost and capability. Selecting the right strategy per query is a practical efficiency problem, yet no routing classifiers have been
arXiv:2603.20895v2 Announce Type: replace Abstract: LLMs often achieve similar average benchmark accuracies while exhibiting complementary strengths on different subsets of queries, suggesting that a router with query-specific model selection can outperform any single model. While existing routers r
arXiv:2603.22455v4 Announce Type: replace Abstract: Reusable skills let LLM agents package task-specific procedures, tool affordances, and execution guidance into modular building blocks. As skill ecosystems grow to tens of thousands of entries, exposing every skill at inference time becomes infeasi