LLM Routing

LLM: Large Language Model

Ask about this topic

Overview

Large language model routing studies how to assign a query, workflow step, or token to an appropriate model, expert, tool, retrieval path, or amount of computation. Common approaches use query features, confidence or uncertainty, hidden-state signals, and response disagreement to choose a capable low-cost option or escalate when needed, using classifiers, contextual bandits, reinforcement learning, and calibrated cascades. Systems work also schedules heterogeneous models and GPUs around budgets, latency, energy, cache reuse, privacy, and service guarantees, with evaluations spanning reasoning, coding, question answering, retrieval-augmented generation, agents, and production workloads. A central tension is that oracle model choices can show substantial gains, while deployable routers depend on reliable quality estimates and supervision and can falter under distribution shifts, weak model specialization, noisy evaluation, or routing overhead.

Latest papers

CardsList

355 papers54 papers in the last four weeks, up 35% on the four weeks before. 0.3% of all new papers.

Mar 30, 2026

Privacy Guard & Token Parsimony by Prompt and Context Handling and LLM Routing

The large-scale adoption of Large Language Models (LLMs) forces a trade-off between operational cost (OpEx) and data privacy. Current routing frameworks reduce costs but ignore prompt sensitivity, exposing users and institutions to leakage risks towards third-party cloud providers. We formalise the "Inseparability Paradigm": advanced context management intrinsically coincides with privacy management. We propose a local "Privacy Guard" -- a holistic contextual observer powered by an on-premise Small Language Model (SLM) -- that performs abstractive summarisation and Automatic Prompt Optimisation (APO) to decompose prompts into focused sub-tasks, re-routing high-risk queries to Zero-Trust or NDA-covered models. This dual mechanism simultaneously eliminates sensitive inference vectors (Zero Leakage) and reduces cloud token payloads (OpEx Reduction). A LIFO-based context compacting mechanism further bounds working memory, limiting the emergent leakage surface. We validate the framework through a 2x2 benchmark (Lazy vs. Expert users; Personal vs. Institutional secrets) on a 1,000-sample dataset, achieving a 45% blended OpEx reduction, 100% redaction success on personal secrets, and -- via LLM-as-a-Judge evaluation -- an 85% preference rate for APO-compressed responses over raw baselines. Our results demonstrate that Token Parsimony and Zero Leakage are mathematically dual projections of the same contextual compression operator.

Alessio Langiu

National Research Council of Italy - Institute of Marine Sciences (CNR-ISMAR)

Privacy Protection for LLM AgentsPrivacy Leakage in Language ModelsLLM RoutingLLM Context ManagementPrivacy-Preserving Language ModelsLLM Inference Efficiency+1
AskPDF
Mar 28, 2026

From Inference Routing to Agent Orchestration: Declarative Policy Compilation with Cross-Layer Verification

The Semantic Router DSL is a non-Turing-complete policy language deployed in production for per-request LLM inference routing: content signals (embedding similarity, PII detection, jailbreak scoring) feed into weighted projections and priority-ordered decision trees that select a model, enforce privacy policies, and produce structured audit traces -- all from a single declarative source file. Prior work established conflict-free compilation for probabilistic predicates and positioned the DSL within the Workload-Router-Pool inference architecture. This paper extends the same language from stateless, per-request routing to multi-step agent workflows -- the full path from inference gateway to agent orchestration to infrastructure deployment. The DSL compiler emits verified decision nodes for orchestration frameworks (LangGraph, OpenClaw), Kubernetes artifacts (NetworkPolicy, Sandbox CRD, ConfigMap), YANG/NETCONF payloads, and protocol-boundary gates (MCP, A2A) -- all from the same source. Because the language is non-Turing-complete, the compiler guarantees exhaustive routing, conflict-free branching, referential integrity, and audit traces structurally coupled to the decision logic. Because signal definitions are shared across targets, a threshold change propagates from inference gateway to agent gate to infrastructure artifact in one compilation step -- eliminating cross-team coordination as the primary source of policy drift. We ground the approach in four pillars -- auditability, cost efficiency, verifiability, and tunability -- and identify the verification boundary at each layer.

Huamin Chen, Xunzhuo Liu, Bowei He +1

vLLM Semantic Router Project · MBZUAI · McGill University +1

LLM RoutingLLM Agent OrchestrationAI Agent GovernanceFormal VerificationAI Agent Auditing
AskPDF
Mar 28, 2026

Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation

Large Language Models (LLMs) exhibit a well-documented positional bias when processing long input contexts: information in the middle of a context window receives substantially less attention than content at the boundaries, a phenomenon termed the Lost-in-the-Middle effect (Liu et al., 2024). This limits knowledge-retrieval applications that embed large structured knowledge bases directly in the LLM context. Retrieval-Augmented Generation (RAG) addresses scalability by retrieving only relevant fragments, but introduces substantial infrastructure overhead and is ill-suited to libraries whose semantic boundaries are human-defined rather than statistically learned. We propose Self-Describing Structured Retrieval (SDSR), a lightweight framework in which structured data files embed human-authored navigational metadata at the file's primacy position, thereby exploiting rather than fighting the LLM's primacy bias. We further propose a Dual-Layer Guidance strategy combining in-file metadata with explicit routing rules in the system prompt. We validate SDSR through a four-round benchmark using a 190-skill library expanded from 36 to 119 categories via adversarial distractor injection. Four conditions are tested: (A) no guidance, (B) in-file summary only, (C) prompt hint only, (D) both combined. Version D achieves 100% primary routing accuracy (20/20) at 119 categories versus 65% for the no-guidance baseline. We identify a fundamental asymmetry: primary routing is solvable by explicit rules, while secondary cross-category routing requires architectural intent explicitly encoded in the data structure. We further extend SDSR to semi-structured corpora, showing how cross-reference encoding enables operation without vector databases in domains with recoverable document structure.

Hung Ming Liu

PARRAWA AI

Lost-in-the-Middle EffectInformation RetrievalLLM RoutingLLM Prompting
AskPDF
Mar 27, 2026

MemBoost: A Memory-Boosted Framework for Cost-Aware LLM Inference

Large Language Models (LLMs) deliver strong performance but incur high inference cost in real-world services, especially under workloads with repeated or near-duplicate queries across users and sessions. In this work, we propose MemBoost, a memory-boosted LLM serving framework that enables a lightweight model to reuse previously generated answers and retrieve relevant supporting information for cheap inference, while selectively escalating difficult or uncertain queries to a stronger model. Unlike standard retrieval-augmented generation, which primarily grounds a single response, MemBoost is designed for interactive settings by supporting answer reuse, continual memory growth, and cost-aware routing. Experiments across multiple models under simulated workloads show that MemBoost substantially reduces expensive large-model invocations and overall inference cost, while maintaining high answer quality comparable to the strong model baseline.

Joris Köster, Zixuan Liu, Siavash Khajavi +1

Department of Computer Science, Aalto University, Finland · Department of Computer Science, Tulane University, LA, USA · Department of Industrial Engineering and Management, Aalto University, Finland

LLM Inference ServingCost-Aware InferenceLLM RoutingMemory-Augmented Language Models
AskPDF
Mar 26, 2026

Runtime Burden Allocation for Structured LLM Routing in Agentic Expert Systems: A Full-Factorial Cross-Backend Methodology

Structured LLM routing is often treated as a prompt-engineering problem. We argue that it is, more fundamentally, a systems-level burden-allocation problem. As large language models (LLMs) become core control components in agentic AI systems, reliable structured routing must balance correctness, latency, and implementation cost under real deployment constraints. We show that this balance is shaped not only by prompts or schemas, but also by how structural work is allocated across the generation stack: whether output structure is emitted directly by the model, compressed during transport, or reconstructed locally after generation. We evaluate this formulation through a comprehensive full-factorial benchmark covering 48 deployment configurations and 15,552 requests across OpenAI, Gemini, and Llama backends. Our central finding is consequential: there is no universal best routing mode. Instead, backend-specific interaction effects dominate performance. Modes that remain highly reliable on Gemini and OpenAI can suffer substantial correctness degradation on Llama, while efficiency gains from compressed realization are strongly backend-dependent. Rather than presenting another isolated model comparison, this work contributes a deployable framework for reasoning about structured routing under heterogeneous backend conditions. We provide a cross-backend evaluation methodology and practical deployment guidance for navigating the correctness-cost-latency frontier in production-grade agentic expert systems.

Zhou Hanlin, Chan Huah Yong

School of Computer Sciences, Universiti Sains Malaysia (USM), Penang, Malaysia · Xiamen Software Vocational & Technical College, Xiamen, China

LLM RoutingLLM EvaluationLLM Inference EfficiencyLLM Serving
AskPDF
Mar 26, 2026

Evaluating Small Language Models for Front-Door Routing: A Harmonized Benchmark and Synthetic-Traffic Experiment

Selecting the appropriate model at inference time -- the routing problem -- requires jointly optimizing output quality, cost, latency, and governance constraints. Existing approaches delegate this decision to LLM-based classifiers or preference-trained routers that are themselves costly and high-latency, reducing a multi-objective optimization to single-dimensional quality prediction. We argue that small language models (SLMs, 1-4B parameters) have now achieved sufficient reasoning capability for sub-second, zero-marginal-cost, self-hosted task classification, potentially making the routing decision negligible in the inference budget. We test this thesis on a six-label taxonomy through two studies. Study 1 is a harmonized offline benchmark of Phi-3.5-mini, Qwen2.5-1.5B, and Qwen-2.5-3B on identical Azure T4 hardware, serving stack, quantization, and a fixed 60-case corpus. Qwen-2.5-3B achieves the best exact-match accuracy (0.783), the strongest latency-accuracy tradeoff, and the only nonzero accuracy on all six task families. Study 2 is a pre-registered four-arm randomized experiment under synthetic traffic with an effective sample size of 60 unique cases per arm, comparing Phi-4-mini, Qwen-2.5-3B, and DeepSeek-V3 against a no-routing control. DeepSeek-V3 attains the highest accuracy (0.830) but fails the pre-registered P95 latency gate (2,295 ms); Qwen-2.5-3B is Pareto-dominant among self-hosted models (0.793 accuracy, 988 ms median, $0 marginal cost). No model meets the standalone viability criterion (>=0.85 accuracy, <=2,000 ms P95). The cost and latency prerequisites for SLM-based routing are met; the accuracy gap of 6-8 percentage points and the untested question of whether correct classification translates to downstream output quality bound the remaining distance to production viability.

Warren Johnson, Charles Lee

Plexor Labs, Sammamish, WA, USA · Project Autobots, Seattle, WA, USA

LLM RoutingSmall Language ModelsLLM Evaluation
AskPDF
Mar 26, 2026

Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs

Retrieval-augmented generation (RAG) faces a fundamental three-way tension: deeper retrieval improves factual grounding but inflates token costs and end-to-end latency. Static retrieval configurations cannot resolve this tension across heterogeneous query workloads -- simple definitional queries waste budget on unnecessary context, while complex analytical prompts are underserved by shallow retrieval. This paper introduces Cost-Aware RAG (CA-RAG), a per-query routing framework that selects from a discrete catalog of strategy bundles -- each coupling a retrieval depth (from retrieval-free direct inference to top-k=10k{=}10 dense retrieval) with a fixed generation profile -- by maximizing a scalar utility that linearly combines an estimated quality prior with normalized penalties for predicted latency and total billed tokens. CA-RAG is implemented with FAISS-backed dense retrieval and OpenAI chat/embedding APIs, and evaluated on a 28-query benchmark spanning four bundles. The router dynamically exercises all bundles, achieving 26% fewer billed tokens than always-heavy retrieval and 34% lower mean latency than always-direct inference while maintaining equivalent answer quality. Per-query delta analysis reveals that savings are non-uniform and concentrated in simpler queries, motivating complexity-aware guardrails. Sensitivity analysis confirms that the same bundle catalog supports multiple cost-latency-quality operating points through weight adjustment alone. All results are generated directly from logged CSV artifacts for full reproducibility. CA-RAG provides a transparent, auditable foundation for cost-conscious LLM deployments.

Sanjay Mishra

Raleigh, NC, USA

Retrieval-Augmented GenerationAdaptive RAGCost-Aware InferenceLLM RoutingRAG Evaluation
AskPDF
Mar 25, 2026

Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity Constraints

We study the problem of routing queries to large language models (LLMs) under cost, GPU resources, and concurrency constraints. Prior per-query routing methods often fail to control batch-level cost, especially under non-uniform or adversarial batching. To address this, we propose a batch-level, resource-aware routing framework that jointly optimizes model assignment for each batch while respecting cost and model capacity limits. We further introduce a robust variant that accounts for uncertainty in predicted LLM performance, along with an offline instance allocation procedure that balances quality and throughput across multiple models. Experiments on two multi-task LLM benchmarks show that robustness improves accuracy by 1-14% over non-robust counterparts (depending on the performance estimator), batch-level routing outperforms per-query methods by up to 24% under adversarial batching, and optimized instance allocation yields additional gains of up to 3% compared to a non-optimized allocation, all while strictly controlling cost and GPU resource constraints.

Jelena Markovic-Voronov, Kayhan Behdin, Yuanda Xu +3

LinkedIn · MIT

LLM RoutingLLM Inference SchedulingCost-Aware InferenceRobust Optimization
AskPDF
Mar 25, 2026

ReLope: From Hidden-State Probing to a Decision Module for Multimodal LLM Routing

Routing balances performance and cost in hybrid systems by escalating selected queries from a lightweight model to a powerful but expensive one. Hidden-state probes provide an effective routing signal by predicting the small model's correctness from hidden states it already computes. Although effective in text-only settings, their behavior on multimodal LLMs (MLLMs) is less understood. We find that correctness is harder to predict from hidden states when questions are paired with images rather than with captions of those images. Two training-free dependence measures, HSIC and label CKA, show the same pattern. We first investigate whether changing hidden states used by the probe improves correctness prediction for MLLMs. We propose Attention Probe, which learns an attention query to pool frozen token states into a routing feature and improves over the standard probe. However, pooling only recombines hidden states computed for answer generation, not for deciding whether the answer should be trusted. We therefore build a decision layer inside the existing MLLM and train it for the routing decision. The resulting router, ReLope (KL-Regularized LoRA Probe), adapts a separate copy of one MLLM layer with LoRA and regularizes it with a KL-penalized stochastic bottleneck. This decision branch shares the frozen lower layers and leaves the model's answer-generation path unchanged. ReLope attains the highest correctness prediction AUC on all five benchmarks and three backbones we evaluate and improves the accuracy versus cost trade-off at negligible overhead. These results suggest a new perspective and a practical technical path on routing: rather than reading decisions off states built for generation, routing decisions can be learned by a dedicated decision layer inside the model. Code: https://github.com/Spinozaaa/ReLope

Yaopei Zeng, Congchao Wang, Blake JianHang Chen +1

Pennsylvania State University · Google · Amazon AGI

Multimodal Large Language ModelsLLM RoutingLanguage Model Probing
AskPDF
Mar 25, 2026

GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization

Worldwide image geolocalization aims to predict precise GPS coordinates for images captured anywhere on Earth, which is challenging due to the large visual and geographic diversity. Recent methods mainly follow two paradigms: retrieval-based approaches that match queries against a reference database, and generation-based approaches that directly predict coordinates using Large Vision-Language Models (LVLMs). However, we observe distinct error profiles between them: retrieval excels at fine-grained instance matching, while generation offers robust semantic reasoning. This complementary heterogeneity suggests that no single paradigm is universally superior. To harness this potential, we propose GeoRouter, a dynamic routing framework that adaptively assigns each query to the optimal paradigm. GeoRouter leverages an LVLM backbone to analyze visual content and provide routing decisions. To optimize GeoRouter, we introduce a distance-aware preference objective that converts the distance gap between paradigms into a continuous supervision signal, explicitly reflecting relative performance differences. Furthermore, we construct GeoRouting, the first large-scale dataset tailored for training routing policies with independent paradigm predictions. Extensive experiments on IM2GPS3k and YFCC4k demonstrate that GeoRouter significantly outperforms state-of-the-art baselines.

Pengyue Jia, Derong Xu, Yingyi Zhang +5

Department of Data Science, City University of Hong Kong

LLM Routing
AskPDF
Mar 24, 2026

DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Models

The expansion of generative AI and LLM services underscores the growing need for adaptive mechanisms to select an appropriate available model to respond to a user's prompts. Recent works have proposed offline and online learning formulations to identify the optimal generative AI model for an input prompt, based solely on maximizing prompt-based fidelity evaluation scores, e.g., CLIP-Score in text-to-image generation. However, such fidelity-based selection methods overlook the diversity of generated outputs, and hence, they can fail to address potential diversity shortcomings in the generated responses. In this paper, we introduce the Diversity-Aware Kernelized Upper Confidence Bound (DAK-UCB) method as a contextual bandit algorithm for the online selection of generative models with diversity considerations. The proposed DAK-UCB method incorporates both fidelity and diversity-related metrics into the selection process. We design this framework based on prompt-aware diversity score functions that decompose to a two-sample-based expectation over prompt-output pairs in the previous generation rounds. Specifically, we illustrate the application of our framework using joint kernel distance and kernel entropy measures. Our experimental results demonstrate the effectiveness of DAK-UCB in promoting diversity-aware model selection while maintaining fidelity in the generations for a sequence of prompts. The code is available at https://github.com/Donya-Jafari/DAK-UCB.

Donya Jafari, Farzan Farnia

Sharif University of Technology · The Chinese University of Hong Kong

LLM RoutingContextual BanditsGenerative Modeling
AskPDF
Mar 24, 2026

Knowledge Access Beats Model Size: Memory Augmented Routing for Persistent AI Agents

Production AI agents frequently receive user-specific queries that are highly repetitive, with up to 47% being semantically similar to prior interactions, yet each query is typically processed with the same computational cost. We argue that this redundancy can be exploited through conversational memory, transforming repetition from a cost burden into an efficiency advantage. We propose a memory-augmented inference framework in which a lightweight 8B-parameter model leverages retrieved conversational context to answer all queries via a low-cost inference path. Without any additional training or labeled data, this approach achieves 30.5% F1, recovering 69% of the performance of a full-context 235B model while reducing effective cost by 96%. Notably, a 235B model without memory (13.7% F1) underperforms even the standalone 8B model (15.4% F1), indicating that for user-specific queries, access to relevant knowledge outweighs model scale. We further analyze the role of routing and confidence. At practical confidence thresholds, routing alone already directs 96% of queries to the small model, but yields poor accuracy (13.0% F1) due to confident hallucinations. Memory does not substantially alter routing decisions; instead, it improves correctness by grounding responses in retrieved user-specific information. As conversational memory accumulates over time, coverage of recurring topics increases, further narrowing the performance gap. We evaluate on 152 LoCoMo questions (Qwen3-8B/235B) and 500 LongMemEval questions. Incorporating hybrid retrieval (BM25 + cosine similarity) improves performance by an additional +7.7 F1, demonstrating that retrieval quality directly enhances end-to-end system performance. Overall, our results highlight that memory, rather than model size, is the primary driver of accuracy and efficiency in persistent AI agents.

Xunzhuo Liu, Bowei He, Xue Liu +3

vLLM Semantic Router Project · MBZUAI · McGill University +3

Memory-Augmented Language Model AgentsConversational MemoryLLM Inference EfficiencyLLM Routing
AskPDF
Mar 24, 2026

KALAVAI: Predicting When Independent Specialist Fusion Works -- A Quantitative Model for Post-Hoc Cooperative LLM Training

Independently trained domain specialists can be fused post-hoc into a single model that outperforms any individual specialist, and the gain is predictable: gain = 0.82 x divergence - 2.72 (R^2 = 0.856, n=6, 3-26% divergence). This enables practitioners to estimate cooperative value before committing compute. Below ~3.3% divergence, gains approach zero.In the KALAVAI protocol, contributors fine-tune copies of a shared checkpoint independently, then submit for lightweight MoE routing (500 steps). Gains are consistent: +7.72% at 410M (+/-0.02%, 3 seeds), +7.49% at 1B (+/-0.01%, 3 seeds), +6.53% at 6.9B, each over the best specialist. The router matches domain-oracle routing within <10^{-5} nats. Cross-lingual fusion (Tamil/Yoruba/Welsh/Code) achieves +21.76%, with Yoruba perplexity falling 41.9 to 7.7. A 20-contributor federation achieves +16.71% (+/-0.07pp, 3 seeds).Three requirements bound the protocol. Shared initialisation is necessary: checkpoint mismatch degrades routing. Frozen layers are optional below ~10,000 steps and beneficial beyond. Learned routing is essential: uniform averaging degrades by -1.2% vs. best specialist, while any trained router achieves oracle-optimal assignment.

Ramchand Kumaresan

Murai Labs

Language Model MergingMixture-of-Experts Expert SpecializationMixture-of-Experts Language ModelsMixture-of-Experts Fine-TuningLLM RoutingFederated Fine-Tuning
AskPDF
Mar 23, 2026

Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs

Multi-agent applications often execute complex tasks as multi-stage workflows, where each stage is an LLM call whose output becomes part of context for subsequent steps. Existing LLM serving systems largely assume homogeneous clusters with identical model replicas. This design overlooks the potential of heterogeneous deployments, where models of different sizes and capabilities enable finer trade-offs between latency and performance. However, heterogeneity introduces new challenges in scheduling across models with diverse throughput and performance. We present Chimera, a predictive scheduling system for multi-agent workflow serving on heterogeneous LLM clusters that jointly improves end-to-end latency and task performance. Chimera applies semantic routing to estimate per-model confidence scores for each request, predicts the total remaining output length of the workflow, and estimates per-model congestion using in-flight predicted token volumes for load balancing. We evaluate Chimera on representative agentic workflows for code generation and math reasoning using multiple heterogeneous LLM configurations. Across comparable settings, Chimera traces the best latency-performance frontier, reducing end-to-end latency by 1.2--2.4×\times and improving task performance by 8.0-9.5 percentage points on average over competitive baselines including vLLM.

Kangqi Ni, Wenyue Hua, Xiaoxiang Shi +3

University of North Carolina, Chapel Hill · Microsoft · Carnegie Mellon University +2

LLM ServingLLM Inference SchedulingLLM Agent ServingLLM Agent Workflow OptimizationLLM Routing
AskPDF
Mar 22, 2026

The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project

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 embedding models, category-aware semantic caching, user-feedback-driven routing adaptation, hallucination detection, and hierarchical content-safety classification for privacy and jailbreak protection; (2) fleet optimization -- fleet provisioning and energy-efficiency analysis; (3) agentic and multimodal routing -- multimodal agent routing, tool selection, CUA security, and multi-turn context memory and safety; (4) governance and standards -- inference routing protocols and multi-provider API extensions. Each paper tackled a specific problem in LLM inference, but the problems are not independent; for example, fleet provisioning depends on the routing policy, which depends on the workload mix, shifting as organizations adopt agentic and multimodal workloads. This paper distills those results into the Workload-Router-Pool (WRP) architecture, a three-dimensional framework for LLM inference optimization. Workload characterizes what the fleet serves (chat vs. agent, single-turn vs. multi-turn, warm vs. cold, prefill-heavy vs. decode-heavy). Router determines how each request is dispatched (static semantic rules, online bandit adaptation, RL-based model selection, quality-aware cascading). Pool defines where inference runs (homogeneous vs. heterogeneous GPU, disaggregated prefill/decode, KV-cache topology). We map our prior work onto a 3x3 WRP interaction matrix, identify which cells we have covered and which remain open, and propose twenty-one concrete research directions at the intersections, each grounded in our prior measurements, tiered by maturity from engineering-ready to open research.

Huamin Chen, Xunzhuo Liu, Bowei He +5

vLLM Semantic Router Project · MBZUAI · McGill University +3

LLM RoutingLLM Inference ServingLLM Inference Efficiency
AskPDF
Mar 22, 2026

ConsRoute:Consistency-Aware Adaptive Query Routing for Cloud-Edge-Device Large Language Models

Large language models (LLMs) deliver impressive capabilities but incur substantial inference latency and cost, which hinders their deployment in latency-sensitive and resource-constrained scenarios. Cloud-edge-device collaborative inference has emerged as a promising paradigm by dynamically routing queries to models of different capacities across tiers. In this paper, we propose ConsRoute, a lightweight, semantic-aware, and adaptive routing framework that significantly improves inference efficiency while minimizing impact on response quality. Unlike prior routing methods that rely on predicting coarse-grained output quality gaps, ConsRoute leverages a reranker to directly assess the semantic consistency between responses generated by models at different tiers, yielding fine-grained soft supervision signals for routing. To minimize device-side overhead, ConsRoute reuses hidden states from the LLM prefilling stage as compact query representations, avoiding additional encoders or inference passes. Furthermore, these representations are clustered, and Bayesian optimization is employed to learn cluster-specific routing thresholds that dynamically balance quality, latency, and cost under heterogeneous query distributions. Extensive experiments demonstrate that ConsRoute achieves near-cloud performance (>=95%) while reducing end-to-end latency and inference cost by nearly 40%, consistently outperforming existing routing baselines in both response quality and system efficiency.

Haoyu Qiao, Hao Zhang, Shanwen Mao +2

the Department of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China · the National Key Laboratory of Smart Farm Technologies and Systems, Harbin 150001, China · the Department of Computer Science and Technology, Harbin Institute of Technology (ShenZhen), ShenZhen 518055, China

Edge-Cloud Collaborative InferenceLLM RoutingAdaptive Model RoutingLLM Inference EfficiencyCost-Aware Inference
AskPDF
Mar 22, 2026

When Does Content-Based Routing Work? Representation Requirements for Selective Attention in Hybrid Sequence Models

We identify a routing paradox in hybrid sequence models: content-based routing - deciding which tokens deserve expensive attention - requires pairwise computation, and this requirement is inescapable. Through 20+ controlled experiments across three tasks, multiple scales (200K to 1.4B parameters), and 15+ routing mechanisms, we map the routing landscape exhaustively. Every system that achieves high routing precision does so through pairwise token comparison. Every mechanism that avoids pairwise computation fails: recurrent models (Mamba-1.4B: 29%), memory banks (12%), bandits (0.7-3.6%), contrastive pretraining (1.6%), and 12 other approaches all cluster at 1-29%. Routing needs two ingredients: (1) per-token representations with bidirectional context and (2) pairwise token comparison. Bidirectional Mamba (O(n)) + pairwise comparison achieves 99.5%; replacing the full pairwise router with rank-1 projection improves this to 99.7%. Adding one bidirectional layer to frozen Pythia-1B recovers 99.4% routing. Six different O(n) preprocessing mechanisms (bidirectional Mamba, Perceiver inducing points, causal attention with E2E training, sparse attention, bidirectional attention, rank-1 projection) all succeed; global mean pooling (1.9%) and Fourier mixing (0.9%) fail. The routing signal occupies a ~34-dimensional latent subspace, invisible to cosine similarity. Non-learned indices (Bloom filter: 90.9%; BM25: 82.7%) bypass the bottleneck for exact/keyword matching. Combining O(n) bidirectional Mamba with rank-1 pairwise projection yields 99.7% routing at linear inference cost.

Abhinaba Basu

National Institute of Electronics and Information Technology (NIELIT)

Attention RoutingLLM RoutingHybrid Attention
AskPDF
Mar 21, 2026

LLM Router: Rethinking Routing with Prefill Activations

Existing routers rely on semantic query features or handcrafted features, which often fail to capture model-specific failures or intrinsic task difficulty. We instead route using internal LLM activations, specifically the residual stream. Our key idea, Encoder-Target Decoupling, separates the model that produces the predictive signal (the Encoder) from the model whose correctness is being estimated (the Target), allowing open-weight encoders to predict the performance of closed-source target models. We evaluate layerwise geometric probes, finding that Fisher Separability (JJ) effectively identifies informative layers, supported by Effective Dimensionality (deffd_{\mathrm{eff}}) diagnostics. We then utilize a SharedTrunkNet, a joint multi-output MLP that predicts simultaneous correctness probabilities across candidate models using concatenated prefill features. In our experiments, SharedTrunkNet consistently outperforms semantic baselines. At its best, SharedTrunkNet closes 45.58% of the gap between the strongest standalone model and the oracle while achieving 74.31% cost savings relative to the most expensive model. These results demonstrate that prefill activations provide a robust routing signal, establishing activation-based routing as a high-performance alternative to purely semantic selection.

Tanay Varshney, Annie Surla, Michelle Xu +5

NVIDIA

LLM RoutingAdaptive Model RoutingCost-Aware Inference
AskPDF
Mar 20, 2026

RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering

Knowledge graph question answering (KGQA) is a promising approach for mitigating LLM hallucination by grounding reasoning in structured and verifiable knowledge graphs. Existing approaches fall into two paradigms: retrieval-based methods utilize small specialized models, which are efficient but often produce unreachable paths and miss implicit constraints, while agent-based methods utilize large general models, which achieve stronger structural grounding at substantially higher cost. We propose RouterKGQA, a framework for specialized--general model collaboration, in which a specialized model generates reasoning paths and a general model performs KG-guided repair only when needed, improving performance at minimal cost. We further equip the specialized with constraint-aware answer filtering, which reduces redundant answers. In addition, we design a more efficient general agent workflow, further lowering inference cost. Experimental results show that RouterKGQA outperforms the previous best by 3.57 points in F1 and 0.49 points in Hits@1 on average across benchmarks, while requiring only 1.15 average LLM calls per question. Codes and models are available at https://github.com/Oldcircle/RouterKGQA.

Bo Yuan, Hexuan Deng, Xuebo Liu +1

Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China · Zhongguancun Academy, Beijing, China

Knowledge Graph Question AnsweringLLM Reasoning with GraphsLLM Routing
AskPDF
Mar 20, 2026

SEAR: Schema-Based Evaluation and Routing for LLM Gateways

Evaluating production LLM responses and routing requests across providers in LLM gateways requires fine-grained quality signals and operationally grounded decisions. To address this gap, we present SEAR, a schema-based evaluation and routing system for multi-model, multi-provider LLM gateways. SEAR defines an extensible relational schema covering both LLM evaluation signals (context, intent, response characteristics, issue attribution, and quality scores) and gateway operational metrics (latency, cost, throughput), with cross-table consistency links across around one hundred typed, SQL-queryable columns. To populate the evaluation signals reliably, SEAR proposes self-contained signal instructions, in-schema reasoning, and multi-stage generation that produces database-ready structured outputs. Because signals are derived through LLM reasoning rather than shallow classifiers, SEAR captures complex request semantics, enables human-interpretable routing explanations, and unifies evaluation and routing in a single query layer. Across thousands of production sessions, SEAR achieves strong signal accuracy on human-labeled data and supports practical routing decisions, including large cost reductions with comparable quality.

Zecheng Zhang, Han Zheng, Yue Xu

Strukto.AI, USA · Infron.AI, USA

LLM RoutingLLM EvaluationLLM ServingStructured Output Generation
AskPDF
Mar 19, 2026

Scalable Prompt Routing via Fine-Grained Latent Task Discovery

Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools scale to include dozens of frontier models with narrow performance gaps, existing approaches face significant challenges: manually defined task taxonomies cannot capture fine-grained capability distinctions, while monolithic routers struggle to differentiate subtle differences across diverse tasks. We propose a two-stage routing architecture that addresses these limitations through automated fine-grained task discovery and task-aware quality estimation. Our first stage employs graph-based clustering to discover latent task types and trains a classifier to assign prompts to discovered tasks. The second stage uses a mixture-of-experts architecture with task-specific prediction heads for specialized quality estimates. At inference, we aggregate predictions from both stages to balance task-level stability with prompt-specific adaptability. Evaluated on 10 benchmarks with 11 frontier models, our method consistently outperforms existing baselines and surpasses the strongest individual model while incurring less than half its cost.

Yunyi Zhang, Soji Adeshina, Sheng Guan +5

Amazon Web Services

LLM Routing
AskPDF
Mar 19, 2026

TARo: Token-level Adaptive Routing for LLM Test-time Alignment

Large language models (LLMs) exhibit strong reasoning capabilities but typically require expensive post-training to reach high performance. Recent test-time alignment methods offer a lightweight alternative, but have been explored mainly for preference alignment rather than reasoning. To bridge this gap, we propose, Token-level Adaptive Routing (TARo), which steers frozen LLMs toward structured reasoning entirely at inference time. Specifically, we first train reward models on step-wise mathematical traces to capture fine-grained logical consistency signals, then introduce a learnable token-level router that automatically controls the guidance of the reward model to the base model. Extensive experiments show that TARo significantly improves reasoning performance by up to +22.4% over base model and +8.4% over existing token-level test-time alignment methods, while also boosting out-of-distribution clinical reasoning (MedXpertQA) and instruction following (AlpacaEval). Furthermore, TARo also generalizes from small to large backbones without retraining, extending test-time alignment from preference optimization to robust, cross-domain reasoning.

Arushi Rai, Qiang Zhang, Hanqing Zeng +5

Meta · University of Pittsburgh · University of California, Berkeley

Inference-Time Language Model AlignmentLLM ReasoningLLM Routing
AskPDF
Mar 18, 2026

Conflict-Free Policy Languages for Probabilistic ML Predicates: A Framework and Case Study with the Semantic Router DSL

Conflict detection in policy languages is a solved problem -- as long as every rule condition is a crisp Boolean predicate. BDDs, SMT solvers, and NetKAT all exploit that assumption. But a growing class of routing and access-control systems base their decisions on probabilistic ML signals: embedding similarities, domain classifiers, complexity estimators. Two such signals, declared over categories the author intended to be disjoint, can both clear their thresholds on the same query and silently route it to the wrong model. Nothing in the compiler warns about this. We characterize the problem as a three-level decidability hierarchy -- crisp conflicts are decidable via SAT, embedding conflicts reduce to spherical cap intersection, and classifier conflicts are undecidable without distributional knowledge -- and show that for the embedding case, which dominates in practice, replacing independent thresholding with a temperature-scaled softmax partitions the embedding space into Voronoi regions where co-firing is impossible. No model retraining is needed. We implement the detection and prevention mechanisms in the Semantic Router DSL, a production routing language for LLM inference, and discuss how the same ideas apply to semantic RBAC and API gateway policy.

Xunzhuo Liu, Hao Wu, Huamin Chen +2

vLLM Semantic Router Project · MBZUAI / McGill University

LLM Routing
AskPDF
Mar 16, 2026

MoLoRA: Composable Specialization via Per-Token Adapter Routing

Multi-adapter serving systems route entire sequences to a single adapter, forcing a choice when requests span multiple domains. This assumption fails in two important settings: (1) multimodal generation, where text and image tokens require different adapters within the same sequence, and (2) mixed-capability requests like "write code to solve this equation," which need expertise from multiple specialized adapters. We introduce per-token routing, which routes individual tokens to adapters based on either vocabulary structure (for multimodal models) or learned gating (for semantic specialization). Per-token routing is provably optimal, achieving work N for N tokens versus K \cdot N for per-sequence routing with K adapter types. Our key contribution is MoLoRA (Mixture of LoRA), which enables composable specialization: load multiple domain-specific adapters and let a learned router select the appropriate adapter per-token. We demonstrate that specialization dramatically beats scale: MoLoRA enables Qwen3-1.7B to exceed Qwen3-8B across four reasoning benchmarks while being 4.7x smaller. This enables modular expertise at inference time: train focused LoRAs independently, combine them without retraining, and add new capabilities by simply loading new adapters.

Shrey Shah, Justin Wagle

LLM RoutingLow-Rank Adaptation
AskPDF
Mar 16, 2026

Directional Routing in Transformers

We introduce directional routing, a lightweight mechanism that gives each transformer attention head learned suppression directions controlled by a shared router, at 3.9% parameter cost. We train a 433M-parameter model alongside an identical baseline in a single run, then trace the resulting circuits through mechanistic interpretability. Routing becomes the model's dominant computational pathway. Disabling it collapses factual recall to near-zero probability across all 8 test prompts and drops induction accuracy from 93.4% to 0.0%. Knocking out individual attention heads has negligible effect: the primary mover head's removal actually increases target probability, and induction heads retain 98.6% accuracy without their strongest member. The coordination mechanism is irreplaceable; the components it coordinates are not. The model also self-organizes, without explicit pressure, into two regimes: domain-adaptive routing in early layers and fixed syntactic pruning in late layers, where the least-varying layer is the most critical (+42.6 PPL when disabled). Routing reduces perplexity 31-56% relative to the baseline, though downstream multiple-choice benchmarks do not yet reflect these gains.

Kevin Taylor

Attention RoutingTransformerLLM RoutingTransformer Attention
AskPDF
Mar 13, 2026

LLM Routing as Reasoning: A MaxSAT View

Routing a query through an appropriate LLM is challenging, particularly when user preferences are expressed in natural language and model attributes are only partially observable. We propose a constraint-based interpretation of language-conditioned LLM routing, formulating it as a weighted MaxSAT/MaxSMT problem in which natural language feedback induces hard and soft constraints over model attributes. Under this view, routing corresponds to selecting models that approximately maximize satisfaction of feedback-conditioned clauses. Empirical analysis on a 25-model benchmark shows that language feedback produces near-feasible recommendation sets, while no-feedback scenarios reveal systematic priors. Our results suggest that LLM routing can be understood as structured constraint optimization under language-conditioned preferences.

Son Nguyen, Xinyuan Liu, Ransalu Senanayake

Arizona State University

LLM RoutingLarge Language Model-Based Recommendation
AskPDF
Mar 13, 2026

Token-Budget-Aware Pool Routing for Cost-Efficient LLM Inference

Production vLLM fleets provision every instance for worst-case context length, wasting 4-8x concurrency on the 80-95% of requests that are short and simultaneously triggering KV-cache failures -- OOM crashes, preemption storms, and request rejections. Both problems share a single root cause: configuration-traffic mismatch. We propose token-budget-aware pool routing: estimate each request's total token budget using a self-calibrating per-category bytes-per-token ratio, then dispatch it to one of two vLLM pools -- a high-throughput short pool or a high-capacity long pool -- each right-sized for its workload class. The ratio is learned online via exponential moving average from usage.prompt_tokens feedback, requiring no tokenizer. A closed-form cost model, savings = alpha * (1 - 1/rho), predicts fleet-level GPU savings from two observable quantities: the short-traffic fraction alpha and the throughput gain ratio rho. On traces from the Azure LLM Inference Dataset and LMSYS-Chat-1M serving Llama-3-70B on A100 GPUs, token-budget routing reduces GPU instances by 17-39% ($1.2-2.0M/yr at 1,000 req/s), with savings verified by a self-contained discrete-event simulator. A case study projecting Qwen3-235B-A22B on AMD MI300X at 10,000 req/s shows $15.4M/yr in savings. The algorithm adds O(1) dispatch overhead, self-calibrates across content types without a tokenizer, and composes with PagedAttention, continuous batching, and prefill-decode disaggregation.

Huamin Chen, Xunzhuo Liu, Junchen Jiang +2

vLLM Semantic Router Project · Tensormesh Inc / UChicago · MBZUAI / McGill University

LLM Inference EfficiencyLLM RoutingCost-Aware InferenceLLM Request Scheduling
AskPDF
Mar 13, 2026

Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization

Large Language Model (LLM)-driven Multi-Agent Systems (MAS) have demonstrated strong capability in complex reasoning and tool use, and heterogeneous agent pools further broaden the quality--cost trade-off space. Despite these advances, real-world deployment is often constrained by high inference cost, latency, and limited transparency, which hinders scalable and efficient routing. Existing routing strategies typically rely on expensive LLM-based selectors or static policies, and offer limited controllability for semantic-aware routing under dynamic loads and mixed intents, often resulting in unstable performance and inefficient resource utilization. To address these limitations, we propose AMRO-S, an efficient and interpretable routing framework for Multi-Agent Systems (MAS). AMRO-S models MAS routing as a semantic-conditioned path selection problem, enhancing routing performance through three key mechanisms: First, it leverages a supervised fine-tuned (SFT) small language model for intent inference, providing a low-overhead semantic interface for each query; second, it decomposes routing memory into task-specific pheromone specialists, reducing cross-task interference and optimizing path selection under mixed workloads; finally, it employs a quality-gated asynchronous update mechanism to decouple inference from learning, optimizing routing without increasing latency. Extensive experiments on five public benchmarks and high-concurrency stress tests demonstrate that AMRO-S consistently improves the quality--cost trade-off over strong routing baselines, while providing traceable routing evidence through structured pheromone patterns.

Xudong Wang, Chaoning Zhang, Jiaquan Zhang +8

School of Computing, Kyung Hee University, Yongin-si 17104, South Korea · School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China · School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China +1

LLM Agent RoutingLLM RoutingMulti-Agent LLM Systems
AskPDF
Mar 13, 2026

98×\times Faster LLM Routing Without a Dedicated GPU: Flash Attention, Prompt Compression, and Near-Streaming for the vLLM Semantic Router

System-level routers that intercept LLM requests for safety classification, domain routing, and PII detection must be both fast and operationally lightweight: they should add minimal latency to every request, yet not require a dedicated GPU -- an expensive resource better used for LLM inference itself. When the router co-locates on the same GPU as vLLM serving instances, standard attention's O(n2)O(n^2) memory makes long-context classification (8K--32K tokens) impossible: at 8K tokens, three concurrent classifiers need ∼{\sim}4.5,GB for attention masks alone, far exceeding the memory left by vLLM. We present three staged optimizations for the vLLM Semantic Router, benchmarked on AMD Instinct MI300X, that solve both the latency and the memory problem. Stage~1: a custom CK Flash Attention operator for ONNX Runtime on ROCm reduces attention memory from O(n2)O(n^2) to O(n)O(n) and end-to-end (E2E) latency from 4{,}918,ms to 127,ms (\textbf{38.7×\times}), enabling 8K--32K tokens where SDPA OOMs. Stage~2: classical NLP prompt compression (TextRank, position weighting, TF-IDF, and novelty scoring) reduces all inputs to ∼{\sim}512 tokens without neural inference, capping both latency and GPU memory at a constant regardless of original prompt length (E2E 127→\to62,ms, \textbf{2.0×\times}). Stage~3: near-streaming body processing with adaptive chunking and zero-copy JSON eliminates serialization overhead (E2E 62→\to50,ms, \textbf{1.2×\times}). Cumulatively: \textbf{98×\times} improvement (4{,}918,ms to 50,ms), 16K-token routing in 108,ms, and a total router GPU footprint under 800,MB -- small enough to share a GPU with LLM serving and removing the need for a dedicated accelerator. Stage1 targets AMD ROCm (NVIDIA GPUs already have FlashAttention via cuDNN); Stages2 and~3 are hardware-agnostic.

Xunzhuo Liu, Bowei He, Xue Liu +3

vLLM Semantic Router Project · MBZUAI · McGill University +2

LLM RoutingLLM ServingLLM Inference AccelerationAttention Mechanisms
AskPDF
Mar 13, 2026

Outcome-Aware Tool Selection for Semantic Routers: Latency-Constrained Learning Without LLM Inference

Semantic routers in LLM inference gateways select tools in the critical request path, where every millisecond of added latency compounds across millions of requests. We propose Outcome-Aware Tool Selection (OATS), which interpolates tool embeddings toward the centroid of queries where they historically succeed -- an offline process that adds no parameters, latency, or GPU cost at serving time. On MetaTool (199tools, 4,287queries), this improves NDCG@5 from 0.869 to 0.940; on ToolBench (2,413~APIs), from 0.834 to 0.848. We also evaluate two learned extensions: a 2,625-parameter MLP re-ranker and a 197K-parameter contrastive adapter. The MLP re-ranker hurts or matches baseline when outcome data is sparse relative to the tool set; the contrastive adapter provides comparable gains on MetaTool (NDCG@5: 0.931). All methods are evaluated on the same held-out 30% test split. The practical takeaway is to start with the zero-cost refinement and add learned components only when data density warrants it. All mechanisms run within single-digit millisecond CPU budgets.

Huamin Chen, Xunzhuo Liu, Junchen Jiang +2

vLLM Semantic Router Project · Tensormesh Inc / UChicago · MBZUAI / McGill University

LLM RoutingLLM Tool UseLearning to RankCost-Aware Inference
AskPDF