{"total":22,"rows":[{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238,"area":null},{"id":"2404.10136","title":"Language Model Cascades: Token-level uncertainty and beyond","created":"2024-04-15","cited_by_count":121,"area":null},{"id":"2407.10834","title":"MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs","created":"2024-07-15","cited_by_count":41,"area":null},{"id":"2510.00202","title":"RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers","created":"2025-09-30","cited_by_count":22,"area":null},{"id":"2502.00409","title":"Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems","created":"2025-02-01","cited_by_count":20,"area":null},{"id":"2508.12491","title":"Cost-Aware Contrastive Routing for LLMs","created":"2025-08-17","cited_by_count":16,"area":null},{"id":"2406.00060","title":"Cascade-Aware Training of Language Models","created":"2024-05-29","cited_by_count":15,"area":null},{"id":"2501.09345","title":"Rational Tuning of LLM Cascades via Probabilistic Modeling","created":"2025-01-16","cited_by_count":10,"area":null},{"id":"2410.02173","title":"Efficiently Deploying LLMs with Controlled Risk","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2506.06579","title":"Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques","created":"2025-06-06","cited_by_count":5,"area":null},{"id":"2507.03834","title":"Economic Evaluation of LLMs","created":"2025-07-04","cited_by_count":5,"area":null},{"id":"2509.14899","title":"CARGO: A Framework for Confidence-Aware Routing of Large Language Models","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2310.19902","title":"Herd: Using multiple, smaller LLMs to match the performances of proprietary, large LLMs via an intelligent composer","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2512.09386","title":"CONCUR: A Framework for Continual Constrained and Unconstrained Routing","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2606.07392","title":"Online Pandora's Box for Contextual LLM Cascading","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2608.02415","title":"Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2405.19631","title":"Leveraging Open-Source Large Language Models for encoding Social Determinants of Health using an Intelligent Router","created":"2024-05-30","cited_by_count":0,"area":null},{"id":"2509.24814","title":"A Greedy PDE Router for Blending Neural Operators and Classical Methods","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2605.17110","title":"Capturing LLM Capabilities via Evidence-Calibrated Query Clustering","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.17288","title":"When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2607.22561","title":"Codifying the Judge: Scalable Evaluation via Program Distillation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2610.02516","title":"Student-Guided Teacher Distillation for Efficient LLM Task Routing: Positioning Against Jev-Style System-1 Classifiers","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}