{"total":74,"rows":[{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238,"area":null},{"id":"2502.18036","title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","created":"2025-02-25","cited_by_count":86,"area":null},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2502.03261","title":"CARROT: A Cost Aware Rate Optimal Router","created":"2025-02-05","cited_by_count":39,"area":null},{"id":"2405.02134","title":"Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selection","created":"2024-05-03","cited_by_count":33,"area":null},{"id":"2502.14855","title":"Prompt-to-Leaderboard","created":"2025-02-20","cited_by_count":30,"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":"2506.17670","title":"Online Multi-LLM Selection via Contextual Bandits under Unstructured Context Evolution","created":"2025-06-21","cited_by_count":19,"area":null},{"id":"2508.12491","title":"Cost-Aware Contrastive Routing for LLMs","created":"2025-08-17","cited_by_count":16,"area":null},{"id":"2502.09054","title":"Cost-Saving LLM Cascades with Early Abstention","created":"2025-02-13","cited_by_count":14,"area":null},{"id":"2412.12170","title":"PickLLM: Context-Aware RL-Assisted Large Language Model Routing","created":"2024-12-12","cited_by_count":13,"area":null},{"id":"2506.00911","title":"Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models","created":"2025-06-01","cited_by_count":12,"area":null},{"id":"2506.11887","title":"Cascaded Language Models for Cost-effective Human-AI Decision-Making","created":"2025-06-13","cited_by_count":11,"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":"2602.03478","title":"When Routing Collapses: On the Degenerate Convergence of LLM Routers","created":"2026-02-03","cited_by_count":10,"area":null},{"id":"2505.19947","title":"MESS+: Dynamically Learned Inference-Time LLM Routing in Model Zoos with Service Level Guarantees","created":"2025-05-26","cited_by_count":9,"area":null},{"id":"2510.00841","title":"LLM Routing with Dueling Feedback","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2601.21795","title":"Effective LoRA Adapter Routing using Task Representations","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2603.04444","title":"vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models","created":"2026-02-23","cited_by_count":6,"area":null},{"id":"2603.25450","title":"Cross-Model Disagreement as a Label-Free Correctness Signal","created":"2026-03-26","cited_by_count":6,"area":null},{"id":"2410.02173","title":"Efficiently Deploying LLMs with Controlled Risk","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2411.07858","title":"Verbosity $\\neq$ Veracity: Demystify Verbosity Compensation Behavior of Large Language Models","created":"2024-11-12","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":"2510.19208","title":"DiSRouter: Distributed Self-Routing for LLM Selections","created":"2025-10-22","cited_by_count":5,"area":null},{"id":"2505.05049","title":"UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model","created":"2025-05-08","cited_by_count":4,"area":null},{"id":"2601.19402","title":"PROTEUS: SLA-Aware Routing via Lagrangian RL for Multi-LLM Serving Systems","created":"2026-01-27","cited_by_count":4,"area":null},{"id":"2604.25591","title":"Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models","created":"2026-04-28","cited_by_count":4,"area":null},{"id":"2605.06350","title":"Is Escalation Worth It? On the Depth of LLM Cascades","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2608.06867","title":"LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers","created":"2026-08-07","cited_by_count":4,"area":null},{"id":"2505.13425","title":"Learnware of Language Models: Specialized Small Language Models Can Do Big","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2506.17254","title":"Near-Optimal Online Deployment and Routing for Streaming LLMs","created":"2025-06-08","cited_by_count":3,"area":null},{"id":"2510.15346","title":"When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2601.22318","title":"Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluations","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2606.19376","title":"Cost-Optimal LLM Routing with Limited User Feedback under User Satisfaction Guarantees","created":"2026-06-12","cited_by_count":3,"area":null},{"id":"2608.11772","title":"Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction","created":"2026-08-12","cited_by_count":3,"area":null},{"id":"2609.32160","title":"Typed Decision Models: An Early Evidence Audit and Evaluation Checklist","created":"2026-09-26","cited_by_count":3,"area":null},{"id":"2404.15153","title":"Performance Characterization of Expert Router for Scalable LLM Inference","created":"2024-04-22","cited_by_count":2,"area":null},{"id":"2601.22132","title":"Pay for Hints, Not Answers: LLM Shepherding for Cost-Efficient Inference","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2604.17827","title":"Local-First Intelligence via Proactive SLM Collaborating with Feedback-Providing LLM","created":"2026-04-20","cited_by_count":2,"area":null},{"id":"2608.17994","title":"Judge, Retrieve, or Abstain: Uncertainty-Guarded LLM Judging with Provable Risk Guarantees","created":"2026-08-18","cited_by_count":2,"area":null},{"id":"2411.09837","title":"Real-time Adapting Routing (RAR): Improving Efficiency Through Continuous Learning in Software Powered by Layered Foundation Models","created":"2024-11-14","cited_by_count":1,"area":null},{"id":"2412.12701","title":"Trigger$^3$: Refining Query Correction via Adaptive Model Selector","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2603.21237","title":"ConsRoute:Consistency-Aware Adaptive Query Routing for Cloud-Edge-Device Large Language Models","created":"2026-03-22","cited_by_count":1,"area":null},{"id":"2603.22404","title":"Computational Arbitrage in AI Model Markets","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2604.15728","title":"Privacy-Preserving LLMs Routing","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2606.00251","title":"Capability Self-Assessment in Large Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.14350","title":"Design Methodology and Performance Trade-offs Management for Distributed and Compound AI Systems","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2606.18774","title":"RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2607.08665","title":"Resample or Reroute? Recoverable Stopping Debt Without Identified Action Selection","created":"2026-07-09","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":"2503.16893","title":"Improving the End-to-End Efficiency of Offline Inference for Multi-LLM Applications Based on Sampling and Simulation","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2603.23013","title":"Knowledge Access Beats Model Size: Memory Augmented Routing for Persistent AI Agents","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.02367","title":"Evaluating Small Language Models for Front-Door Routing: A Harmonized Benchmark and Synthetic-Traffic Experiment","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.14531","title":"TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification","created":"2026-04-16","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":"2605.24299","title":"LLMs Show No Signs Of Individuated Metacognition","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.20295","title":"Token-Operations-Oriented Inference Optimization Techniques for Large Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.31163","title":"ComplianceGate: Classifier-Gated Multi-Tier LLM Routing for Inference in Regulated Industries","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.23121","title":"SMART: LLM-Augmented Hybrid Retrieval for Dynamic Product Ads","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2607.25018","title":"Conformal Cascade: Distribution-Free Accuracy Guarantees for Multi-Tier LLM Inference","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.08528","title":"Task-to-Model Optimization for Enterprise LLM Coding Assistants: A Data-Driven Framework for Cost-Optimal Routing","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2609.01335","title":"Bandits in Prod: Hyperparameter Optimization at Inference Time","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.01345","title":"Cheap Verifiers, Large Blind Spots: Measuring the Reliability Cost of Cost-Saving Cascades","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.02292","title":"SCX Router: Streaming Zero-Shot Model Selection with a Decoder-KV Classifier and a Real-World Task Ontology","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.15992","title":"Optimal Model Activation Policies for Inference Networks of Large Language Models","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2609.37362","title":"Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37402","title":"Routing Should Pay for Itself: Sparse Supervision for Economical LLM Routing","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.01110","title":"How Much Can Language Models Gain from Test-Time Computation?","created":"2026-10-01","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},{"id":"2610.03296","title":"JOVE: Joint Execution and Verification for Resource-Aware LLM Task Graphs","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.09981","title":"Sensitive-Topic Leakage Through LLM Routing Metadata: Measurement and Mitigation","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.14772","title":"How Should a Camera-First AI Agent Work?","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}