Knowledge catalogue
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. Recent
arXiv:2605.28112v1 Announce Type: cross Abstract: Federated Retrieval-Augmented Generation (FedRAG) is attractive for privacy-sensitive applications because raw data remain local. As a result, routing
arXiv:2604.14246v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models have achieved remarkable scalability, yet they remain vulnerable to hallucinations, particularly when processing
arXiv:2610.07333v1 Announce Type: cross Abstract: As Mixture-of-Experts (MoE) models scale toward hundreds of experts and higher top-k routing, memory efficiency in distributed training becomes a crit
arXiv:2610.07354v1 Announce Type: new Abstract: Deciding when to escalate a query from a small language model to a larger one requires a cheap signal that predicts, before the large model is called, w
arXiv:2610.02808v1 Announce Type: new Abstract: Adaptive multi-verifier systems are commonly compared through endpoint quality-cost gaps, even when the verifier catalog, availability, accounting, info
arXiv:2610.02701v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models can increase parameter capacity without proportionally increasing active computation, but it is unclear how this trade-o
arXiv:2610.01535v1 Announce Type: cross Abstract: Safety routers send each request to one of several models and are judged against the best single model. A major routing benchmark picks that comparato
arXiv:2608.29058v1 Announce Type: new Abstract: Dynamic sparse attention can reduce the quadratic cost of long-context prefilling without changing model weights. MInference assigns each attention head
arXiv:2608.28726v1 Announce Type: new Abstract: The remarkable performance of multimodal large language models (MLLMs) comes at the cost of substantial computational overhead, posing significant chall
arXiv:2604.03592v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models exhibit striking performance disparities across languages, yet the internal mechanisms driving these gaps rema
arXiv:2607.18098v2 Announce Type: replace Abstract: Large language models are increasingly used in practical systems, making efficient model selection important for reducing deployment cost. LLM routi
arXiv:2608.24859v1 Announce Type: new Abstract: Multi-task vehicle routing problem (VRP) solvers seek to handle multiple VRP variants within a single unified model, avoiding the need to train a separa
arXiv:2608.21236v1 Announce Type: new Abstract: Representation engineering offers a lightweight means of controlling language-model behavior by modifying intermediate hidden states, but its direct app
arXiv:2608.14205v1 Announce Type: new Abstract: Load imbalance poses a major bottleneck to the efficiency of expert parallelism in distributed inference of Mixture-of-Experts (MoE) models. The most he
arXiv:2608.13799v1 Announce Type: new Abstract: This paper presents an event-driven learning and benchmarking framework for the Dynamic Multi-Depot Vehicle Routing Problem with progressively revealed
arXiv:2608.12127v1 Announce Type: new Abstract: Model routing aims to select the most suitable model from a candidate pool for each query, balancing quality and cost. Existing VLM routing research is
arXiv:2608.05872v1 Announce Type: cross Abstract: Standard Large Language Models (LLMs) execute layers sequentially. Dynamic layer routing, i.e. search for a different execution path through layers in
New research from Google DeepMind on effective model routing. LLM routers get judged on accuracy and cost. Both can look great while the router is meaningless. If every model in your society responds
arXiv:2606.06924v1 Announce Type: new Abstract: Existing LLM routing methods typically treat a model's single response to a query as its capability label for training routers. However, because LLM gen
arXiv:2606.02136v1 Announce Type: new Abstract: Neural asymmetric routing models increasingly encode directionality through matrix representations and asymmetry-aware attention. The final routing acti
arXiv:2605.29310v1 Announce Type: new Abstract: Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent methods for
arXiv:2603.04445v2 Announce Type: replace-cross Abstract: The rapid growth of large language models (LLMs) with diverse capabilities, costs, and domains has created a critical need for intelligent mod
arXiv:2610.13278v1 Announce Type: new Abstract: Vision-language models (VLMs) exhibit complementary capabilities, yet selecting the most suitable expert for a given image-question query remains challe
arXiv:2606.14929v2 Announce Type: replace-cross Abstract: Modern recommendation systems increasingly rely on dynamically routing diverse queries to multiple embedding models. Despite its practical sig
arXiv:2609.30837v1 Announce Type: cross Abstract: Multi-teacher on-policy distillation (MOPD) integrates specialized capabilities into a single student, but existing practice typically hard-routes eac
arXiv:2609.17542v1 Announce Type: new Abstract: Large language model services increasingly route each query to one of several models of differing capability, using a cheap estimate of query complexity
arXiv:2609.18779v1 Announce Type: new Abstract: Current Mixture-of-Agents (MoA) paradigms generally treat query routing and agent fine-tuning as separate processes, limiting their ability to respond t
arXiv:2609.13742v1 Announce Type: new Abstract: Multimodal Continual Instruction Tuning (MCIT) aims to exploit the incrementally accumulated knowledge to process multimodal inputs of diverse tasks, wh
arXiv:2609.06403v1 Announce Type: new Abstract: Test-time scaling produces cohorts of reasoning rollouts, yet there is no standard label-free account of how their internal computation reorganizes as i
Amazon SageMaker Inference now offers prefix-aware routing, a routing strategy that sends requests sharing the same prompt prefix to the same instance so the KV cache stays warm. In benchmarks on Llam
arXiv:2608.20316v1 Announce Type: new Abstract: Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improve quality and efficiency by routing
arXiv:2608.06607v1 Announce Type: new Abstract: Most document-extraction systems use a single model for all documents. This is simple but can be costly for easy cases and less effective for difficult
arXiv:2608.06400v1 Announce Type: new Abstract: Reward models are central to learning from human preferences, yet identifying what drives their predictions remains challenging. Recent sparse Mixture-o
arXiv:2608.04434v1 Announce Type: new Abstract: Recent large language models (LLMs) have demonstrated remarkable progress in constraint-aware navigation, maze reasoning, and graph reasoning. However,
arXiv:2608.04084v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) networks pursue specialization through learned routers, gates, and load-balancing losses, yet at matched total-parameter budg
arXiv:2607.20981v1 Announce Type: new Abstract: Efficient multimodal inference is increasingly constrained not only by model quality or FLOP count, but also by the cost of preserving, moving, routing,
arXiv:2606.26125v1 Announce Type: cross Abstract: Emerging 6G and edge-intelligent networks require effective and balanced routing algorithms among varied and spatially distributed devices. Existing f
arXiv:2606.12816v3 Announce Type: replace-cross Abstract: Quantum circuit routing is a key step in compiling programs for noisy intermediate-scale quantum processors. Routes that appear efficient by s
arXiv:2605.18094v1 Announce Type: new Abstract: We study the Compositional Geometry Routing Problem (CGRP), a unified superclass of traditional routing problems that covers point-only, line-only, area
arXiv:2605.17571v1 Announce Type: new Abstract: Class-incremental learning (CIL) requires models to learn new classes sequentially while preserving prior knowledge. Recently, approaches that combine p
arXiv:2601.21349v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models scale neural networks by conditionally activating a small subset of experts, where the router plays a central
arXiv:2603.27141v2 Announce Type: replace Abstract: Demographic prompts are routed differently from neutral prompts in Mixture-of-Experts (MoE) language models, motivating tests of routing-level stere
arXiv:2602.04448v3 Announce Type: replace Abstract: Mixture-of-Experts (MoE) language models introduce unique challenges for safety alignment due to their sparse routing mechanisms, which can enable d
arXiv:2609.38585v1 Announce Type: cross Abstract: Existing Large Language Model (LLM) routing methods score LLMs independently to select top-k models. However, this ignores model correlations and enfo
arXiv:2609.35443v2 Announce Type: replace Abstract: Large-scale routing problems are difficult to solve efficiently as their search spaces grow rapidly with problem size. Existing approaches primarily
arXiv:2609.11452v1 Announce Type: new Abstract: Efficient routing optimization is essential to freight transportation, urban logistics, and shared mobility, where high-quality heuristics are often req
arXiv:2609.03707v1 Announce Type: new Abstract: We present our submission to the IJCAI 2025 'Counterfactual Routing Competition' (CRC 25). The goal of the competition is to find counterfactual explana
arXiv:2609.02282v1 Announce Type: cross Abstract: Mineral image classification is important for geological exploration and resource development, but it remains challenging due to substantial intra-cla
arXiv:2608.22788v1 Announce Type: new Abstract: Large-scale rollouts have become a core component of modern LLM systems, spanning reinforcement learning (RL) post-training, on-policy distillation (OPD
arXiv:2608.15102v1 Announce Type: new Abstract: We investigate whether Mixture-of-Experts (MoE) language models develop linguistically structured expert routing during bilingual language acquisition.
It makes sense to optimize model routing at the harness layer instead of the gateway layer if you want to hillclimb on accuracy/cost for any e2e task. Every task is solved by a combination of a model
arXiv:2608.12322v1 Announce Type: cross Abstract: Self-reflection is widely assumed to improve LLM reasoning, yet which component drives the gain remains poorly understood. We present a controlled six
arXiv:2602.07216v2 Announce Type: replace Abstract: Neural combinatorial optimization (NCO) trains fast heuristics for routing problems, but planners often need more than a single solve: they ask whic
arXiv:2608.02674v1 Announce Type: cross Abstract: With the widespread deployment of large foundation models (LFMs) in open environments, safety threats are shifting from black-box jailbreaks toward wh
arXiv:2601.01856v3 Announce Type: replace Abstract: Feature-based anomaly detection is widely adopted in industrial inspection due to the strong representational power of large pre-trained vision enco
arXiv:2607.22465v1 Announce Type: cross Abstract: Routing to select large language models (LLMs) with different cost-quality trade-offs has become a fundamental deployment feature of enterprise AI. Ex
arXiv:2607.04085v1 Announce Type: cross Abstract: Routing-prediction federated learning has emerged as a new paradigm that reframes inter-client heterogeneity as a resource for system-level intelligen
arXiv:2606.28925v1 Announce Type: cross Abstract: Tool and agent routing from natural-language prompts is naturally a set-valued prediction problem: a single query may require multiple agents, while o
arXiv:2603.04444v3 Announce Type: replace-cross Abstract: As large language models (LLMs) diversify across modalities, capabilities, and cost profiles, the problem of intelligent request routing -- se