{"total":32,"rows":[{"id":"2505.19797","title":"The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants","created":"2025-05-26","cited_by_count":38,"area":null},{"id":"2601.07206","title":"LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing","created":"2026-01-12","cited_by_count":38,"area":null},{"id":"2508.12631","title":"Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing","created":"2025-08-18","cited_by_count":34,"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":"2511.07885","title":"Intelligence per Watt: Measuring Intelligence Efficiency of Local AI","created":"2025-11-11","cited_by_count":14,"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":"2603.06616","title":"RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models","created":"2026-02-20","cited_by_count":7,"area":null},{"id":"2510.09852","title":"ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers","created":"2025-10-10","cited_by_count":6,"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":"2509.06274","title":"IPR: Intelligent Prompt Routing with User-Controlled Quality-Cost Trade-offs","created":"2025-09-08","cited_by_count":5,"area":null},{"id":"2607.03436","title":"What Does a Routing Oracle Measure Under Stochastic Decoding? Coupling, Scorer Choice, and Single-Commit Ceilings","created":"2026-07-03","cited_by_count":5,"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":"2608.06867","title":"LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers","created":"2026-08-07","cited_by_count":4,"area":null},{"id":"2608.23023","title":"Most of the LLM Routing Gap Is Task Type","created":"2026-08-24","cited_by_count":4,"area":null},{"id":"2601.05903","title":"HAPS: Hierarchical LLM Routing with Joint Architecture and Parameter Search","created":"2026-01-09","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":"2602.01240","title":"Minimizing Mismatch Risk: A Prototype-Based Routing Framework for Zero-shot LLM-generated Text Detection","created":"2026-02-01","cited_by_count":3,"area":null},{"id":"2602.11877","title":"Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2505.16221","title":"LightRouter: Towards Efficient LLM Collaboration with Minimal Overhead","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2508.05585","title":"DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2605.07075","title":"ModelLens: Finding the Best for Your Task from Myriads of Models","created":"2026-05-08","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":"2609.00482","title":"Are Near-Tied LLM Rankings Robust to Family-DIF-Guided Benchmark Recomposition?","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.38585","title":"FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing","created":"2026-09-29","cited_by_count":1,"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":"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":"2609.30017","title":"Canopy: Exploiting Piecewise Smooth Tree Priors for Multi-Fidelity Bandits","created":"2026-09-24","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":"2610.01627","title":"What Makes Something Hard(er)? Explaining Question Difficulty in Natural Language","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05982","title":"Breaking the Tie: A Cluster-Aware Routing Framework for Large Language Models","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.13276","title":"CopRoute: Dependence-Aware Conformal Routing for Language Models","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}