{"total":23,"rows":[{"id":"2502.20576","title":"OmniRouter: Budget and Performance Controllable Multi-LLM Routing","created":"2025-02-27","cited_by_count":35,"area":null},{"id":"2505.16037","title":"Causal LLM Routing: End-to-End Regret Minimization from Observational Data","created":"2025-05-21","cited_by_count":28,"area":null},{"id":"2511.07885","title":"Intelligence per Watt: Measuring Intelligence Efficiency of Local AI","created":"2025-11-11","cited_by_count":14,"area":null},{"id":"2509.09782","title":"One Head, Many Models: Cross-Attention Routing for Cost-Aware LLM Selection","created":"2025-09-11","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":"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":"2607.09015","title":"Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing","created":"2026-07-10","cited_by_count":3,"area":null},{"id":"2603.02029","title":"Rich Insights from Cheap Signals: Efficient Evaluations via Tensor Factorization","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2509.25535","title":"Meta-Router: Bridging Gold-standard and Preference-based Evaluations in Large Language Model Routing","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2606.07587","title":"The Routing Plateau: Understanding the Accuracy Limits of LLM Routers","created":"2026-05-27","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":"2608.06607","title":"Pre-Inference Routing for Cost-Efficient Document Field Extraction","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2610.02762","title":"Dynamic LLM Routers are Often Misguided","created":"2026-10-02","cited_by_count":1,"area":null},{"id":"2604.00414","title":"Decision-Centric Design for LLM Systems","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2605.07805","title":"Flexible Routing via Uncertainty Decomposition","created":"2026-05-08","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":"2608.12127","title":"SCOPE-Router: Cost-Aware Open-Set VLM Routing for Execution-Oriented Tasks","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.23814","title":"Learning to Grade Efficiently: A Bandit-Driven Prompt-Selection Framework for Low-Cost LLM Essay Scoring","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.04513","title":"Atlas: Optimizing Deployment of Compound AI Workflows on Heterogeneous Clusters","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.32274","title":"When Does a Skill Add Value? Task-Conditional Gain Prediction for Selective Skill Use","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.37902","title":"You Cannot Pick a Provider From the Price List: Market-Aware Routing for Open-Weight LLM Inference","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.07556","title":"Decoupled Multi-Agent Orchestration","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.19198","title":"Embedding Geometry Shapes LLM Routing: Tracing Failure Modes and Improving Generalization","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}