Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads | Paper Citation Record

Observation 94c272d0-7507-4284-b9b4-a1a0799f5355 · outbound

This paper cites Gulavani, Ramachan- dran Ramjee, and Alexey Tumanov.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Gulavani, Ramachan- dran Ramjee, and Alexey Tumanov

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:57.586536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d553330-0b46-45dc-ae72-9ee05ce21503 · outbound

This paper cites Gulavani, Alexey Tumanov, and Ramachandran Ramjee.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Gulavani, Alexey Tumanov, and Ramachandran Ramjee

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:57.664635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e50a210a-996c-4ce1-a368-50be045c6bfd · outbound

This paper cites Alibaba cloud model studio: Model invocation pricing, 2026.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Alibaba cloud model studio: Model invocation pricing, 2026

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:57.765184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1988d571-12fe-4f7b-ab32-c461e4bb4995 · outbound

This paper cites Federate the router: Learning language model routers with sparse and decentralized evaluations, 2026.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Federate the router: Learning language model routers with sparse and decentralized evaluations, 2026

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:57.847003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9eb0e72a-3a9d-4516-ab25-f964eaa85f0f · outbound

This paper cites Optimal scheduling algorithms for llm inference: Theory and practice.Proc.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Optimal scheduling algorithms for llm inference: Theory and practice.Proc

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:58.016742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2882e4c1-6b2d-4506-a53c-8b8f629b6bf4 · outbound

This paper cites Boerner, Stephen Deems, Thomas R.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Boerner, Stephen Deems, Thomas R

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:58.127113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67cb3181-0b62-4b1a-a1b9-ac0a076d55d0 · outbound

This paper cites Learning compact representations of llm abilities via item response theory, 2025.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Learning compact representations of llm abilities via item response theory, 2025

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:58.214930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 337d635a-df40-4270-a9dc-06f8fabde3ef · outbound

This paper cites Frugalgpt: How to use large language models while reducing cost and improving performance.Transactions on Machine Learning Research, 2024.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Frugalgpt: How to use large language models while reducing cost and improving performance.Transactions on Machine Learning Research, 2024

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:58.301940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53536e45-15f4-417e-937b-f5844c40d498 · outbound

This paper cites Block: Balancing Load in LLM Serving with Context, Knowledge and Predictive Scheduling.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Block: Balancing Load in LLM Serving with Context, Knowledge and Predictive Scheduling

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:58.436874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee889630-be2c-4c54-ab3f-9c2fd95a559b · outbound

This paper cites A unified approach to routing and cascading for LLMs.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads A unified approach to routing and cascading for LLMs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:58.544887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea5db281-1b53-4154-9325-4490bbd4262a · outbound

This paper cites an unresolved cited work.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:58.722462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba790edc-b622-499e-9cac-c33e551b1ba9 · outbound

This paper cites an unresolved cited work.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:58.839066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1427b21b-0e0a-4210-84ac-28623b2307ab · outbound

This paper cites Hierarchical neural story generation.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Hierarchical neural story generation

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:58.952345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 691c541f-f017-4fdf-a61d-6d2781a0ecbc · outbound

This paper cites The markov-modulated poisson process (mmpp) cookbook.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads The markov-modulated poisson process (mmpp) cookbook

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:59.046008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd117b2c-c564-4712-be53-68089e231555 · outbound

This paper cites Efficient LLM scheduling by learning to rank.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Efficient LLM scheduling by learning to rank

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:59.175611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c847f8e6-7bb2-40c9-b76c-0e84965261b6 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Gemini: A Family of Highly Capable Multimodal Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:59.294487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c323f8ff-94e5-47e9-ac67-271631dbec0d · outbound

This paper cites Past-future scheduler for llm serving under sla guarantees.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Past-future scheduler for llm serving under sla guarantees

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:59.382553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c3ddefb-1ac5-4aaa-a9b2-35192348b966 · outbound

This paper cites Li, and Richard Socher.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Li, and Richard Socher

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:59.462587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26770c53-fb4b-4c55-86ba-cfa95541c43a · outbound

This paper cites Routerbench: A benchmark for multi-LLM routing system.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Routerbench: A benchmark for multi-LLM routing system

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:59.542939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03f5a96c-5519-45f6-9c5f-917449ee6274 · outbound

This paper cites SLO-Aware Scheduling for Large Language Model Inferences.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads SLO-Aware Scheduling for Large Language Model Inferences

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:59.627222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3948040-18a7-42c1-8505-f1f0860984a3 · outbound

This paper cites Efficient attentions for long document summarization.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Efficient attentions for long document summarization

Reference 21

Resolution: malformed identifier; no resolver link, observed 2026-08-02T14:07:59.709780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6231b84-e9a5-44f9-a2bb-bab933f79809 · outbound

This paper cites Predicting llm inference latency: A roofline-driven ml method.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Predicting llm inference latency: A roofline-driven ml method

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:59.792244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c32df46-bcf5-4941-8ca6-0959b5d8e5d5 · outbound

This paper cites Universal model routing for efficient LLM inference.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Universal model routing for efficient LLM inference

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T14:07:59.951925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99f356c4-6c66-46a0-b2a0-6dd908d90882 · outbound

This paper cites Lightgbm: A highly efficient gradient boosting decision tree.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Lightgbm: A highly efficient gradient boosting decision tree

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:00.010405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6e95019-0927-4f7a-b511-8c979f44582d · outbound

This paper cites Efficient memory management for large language model serving with pagedattention.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Efficient memory management for large language model serving with pagedattention

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:00.095071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f602431-65bb-43a2-96db-3f7d7097cbc2 · outbound

This paper cites Faster, cheaper, just as good: Cost- and latency constrained routing for llms.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Faster, cheaper, just as good: Cost- and latency constrained routing for llms

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:00.184734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 764717b5-0207-464d-a481-3ab4dfb704b5 · outbound

This paper cites Deterministic non-autoregressive neural sequence modeling by iterative refinement.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Deterministic non-autoregressive neural sequence modeling by iterative refinement

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:00.264011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d90e6cd-18dc-4871-ad47-07d53163657f · outbound

This paper cites Fromgenerationtojudgment: Oppor- tunities and challenges of LLM-as-a-judge.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Fromgenerationtojudgment: Oppor- tunities and challenges of LLM-as-a-judge

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:00.349711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb4577bd-b575-4dae-b524-4eb83a24fdc2 · outbound

This paper cites Diffusion-LM improves controllable text generation.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Diffusion-LM improves controllable text generation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:00.435794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f5cfe90-3d48-48e0-8a55-7f22b2c44131 · outbound

This paper cites Throughput-optimal scheduling algorithms for llm inference and ai agents,.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Throughput-optimal scheduling algorithms for llm inference and ai agents,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:00.512272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f20963aa-b673-40bb-b283-be782f28f27f · outbound

This paper cites ROUGE: A package for automatic evaluation of summaries.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads ROUGE: A package for automatic evaluation of summaries

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:00.736056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1a212d1-eb34-4a51-8ea6-a0bb161ed5b6 · outbound

This paper cites Queueing, Predictions, and LLMs: Challenges and Open Problems.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Queueing, Predictions, and LLMs: Challenges and Open Problems

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:00.817791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6903b784-b2cf-416b-b325-7ff3bb088384 · outbound

This paper cites Deferred prefill for throughput maximization in llm inference.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Deferred prefill for throughput maximization in llm inference

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:00.901084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a693ce8b-4157-41f5-a9e0-2ba4dba9d6ca · outbound

This paper cites Nvidia h100 pcie gpu — product brief.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Nvidia h100 pcie gpu — product brief

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:00.978274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a93cffa-6aa5-4d34-a6cb-474202ae568c · outbound

This paper cites Gonzalez, M Waleed Kadous, and Ion Stoica.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Gonzalez, M Waleed Kadous, and Ion Stoica

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:01.058602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f701194-cf7e-4204-ad78-c3bb7a650135 · outbound

This paper cites Proxrouter: Proximity-weighted llm query routing for improved robustness to outliers, 2025.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Proxrouter: Proximity-weighted llm query routing for improved robustness to outliers, 2025

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:01.126930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cab66dec-5dd7-49ed-90a2-d0afedfaaf6c · outbound

This paper cites Locus: Low-dimensional model embeddings for efficient model exploration, comparison, and selection, 2026.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Locus: Low-dimensional model embeddings for efficient model exploration, comparison, and selection, 2026

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:01.212956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b10aa5f2-416a-42e3-b7e6-8d3c79555296 · outbound

This paper cites Queue management for slo-oriented large language model serving.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Queue management for slo-oriented large language model serving

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:01.324988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0cc7d53-d048-4ecf-a8c3-fc982818a9df · outbound

This paper cites Efficiently scaling transformer inference.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Efficiently scaling transformer inference

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:01.577296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40f7be56-8d81-42b3-9471-bc6ae3e318cb · outbound

This paper cites Kalbarczyk, Tamer Başar, and Ravishankar K.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Kalbarczyk, Tamer Başar, and Ravishankar K

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:01.708519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02f6e61f-ed56-4469-83b8-2b901c125e57 · outbound

This paper cites Qwen3 Technical Report.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Qwen3 Technical Report

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:01.830316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f665b1b4-7509-415f-ace1-b0c105c6e4e8 · outbound

This paper cites Don’t stop me now: Embedding based scheduling for llms.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Don’t stop me now: Embedding based scheduling for llms

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:01.966203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f12ea98-663a-4c15-87ab-d9c99f031471 · outbound

This paper cites IRT-router: Effective and interpretable multi-LLM routing via item response theory.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads IRT-router: Effective and interpretable multi-LLM routing via item response theory

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:02.164008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a89824c2-a1ff-47ec-aaa9-623a07dc700d · outbound

This paper cites Llumnix: dynamic scheduling for large language model serving.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Llumnix: dynamic scheduling for large language model serving

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:02.387731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c3c6777-309f-45f6-9d8f-14a0c474dafa · outbound

This paper cites Hashimoto.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Hashimoto

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:02.465271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3331bd0-4fe6-44ea-a110-5a03fc6c2ef9 · outbound

This paper cites ISBN 979-8-89176-251-0.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads ISBN 979-8-89176-251-0

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:02.276883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7cf780b-6b9f-4ce5-b1ba-9dbb71b7c262 · outbound

This paper cites an unresolved cited work.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Unresolved cited work

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:02.635380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3137dcd9-e144-4847-99c0-fec1d0608697 · outbound

This paper cites Cohen, Ruslan Salakhutdinov, and Christo- pher D.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Cohen, Ruslan Salakhutdinov, and Christo- pher D

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:02.730723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f67ff5dd-0810-487c-9c06-2b75c2e36288 · outbound

This paper cites Attention is all you need.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Attention is all you need

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:02.540327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd3715e1-a84c-4d96-8d8c-e88cbe7c0096 · outbound

This paper cites BARTScore: Evaluating generated text as text generation.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads BARTScore: Evaluating generated text as text generation

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:02.980770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e055f8cc-93bb-42a7-bcd9-de6894a6e278 · outbound

This paper cites PhD thesis, Georgia Institute of Technology, August 2009.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads PhD thesis, Georgia Institute of Technology, August 2009

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:03.135243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89d3d3f6-7723-41d2-a43f-f77cbf056a52 · outbound

This paper cites Orca: A distributed serving system for Transformer-Based generative models.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Orca: A distributed serving system for Transformer-Based generative models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:02.828169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 817b5903-4bfd-4603-86f3-1b32786bc0ad · outbound

This paper cites scores". The.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads scores". The

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:03.298249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86558925-525d-475c-b668-498e388567fb · outbound

This paper cites Alternatively, generation work for queries follows the memoryless distribution [34].

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Alternatively, generation work for queries follows the memoryless distribution [34]

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:03.437194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 719892b6-9c99-490c-ac66-de7083f22cc2 · outbound

This paper cites an unresolved cited work.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Unresolved cited work

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:03.579451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c522c42-823f-4001-8522-057759fabc73 · outbound

This paper cites an unresolved cited work.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Unresolved cited work

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:03.701007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83887fa6-2f98-4762-a30d-28e258d74612 · outbound

This paper cites State process and stationary distribution.Queries arrive according to a Poisson process of rateαj, so whenever a new query arrives, the state|Rj(t)| increases by one.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads State process and stationary distribution.Queries arrive according to a Poisson process of rateαj, so whenever a new query arrives, the state|Rj(t)| increases by one

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:03.850772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d867fb0-65e6-4968-8f07-0664ac952bbc · outbound

This paper cites ISBN 9798400712869.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads ISBN 9798400712869

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:01.433404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dfe617e-386a-40c1-9950-183a1a62f5aa · outbound

This paper cites Throughput-Optimal Scheduling Algorithms for LLM Inference and AI Agents.

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads Throughput-Optimal Scheduling Algorithms for LLM Inference and AI Agents

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T14:08:00.632928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers