{"total":86,"rows":[{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61,"area":null},{"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":"2510.09719","title":"ICL-Router: In-Context Learned Model Representations for LLM Routing","created":"2025-10-10","cited_by_count":28,"area":null},{"id":"2505.19435","title":"Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection","created":"2025-05-26","cited_by_count":23,"area":"lr"},{"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":"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":"2603.04445","title":"Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey","created":"2026-02-23","cited_by_count":19,"area":"inference"},{"id":"2508.12491","title":"Cost-Aware Contrastive Routing for LLMs","created":"2025-08-17","cited_by_count":16,"area":null},{"id":"2601.02695","title":"EvoRoute: Experience-Driven Self-Routing LLM Agent Systems","created":"2026-01-06","cited_by_count":16,"area":"agents"},{"id":"2602.02823","title":"R2-Router: A New Paradigm for LLM Routing with Reasoning","created":"2026-02-02","cited_by_count":14,"area":"lr"},{"id":"2509.02718","title":"Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving","created":"2025-09-02","cited_by_count":13,"area":"inference"},{"id":"2509.21164","title":"Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say","created":"2025-09-25","cited_by_count":12,"area":"lr"},{"id":"2607.00053","title":"SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks","created":"2026-06-30","cited_by_count":11,"area":"agents"},{"id":"2510.00844","title":"Learning Compact Representations of LLM Abilities via Item Response Theory","created":"2025-10-01","cited_by_count":10,"area":"moe"},{"id":"2506.16655","title":"Arch-Router: Aligning LLM Routing with Human Preferences","created":"2025-06-19","cited_by_count":9,"area":"alignment"},{"id":"2603.07915","title":"Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents","created":"2026-03-09","cited_by_count":8,"area":"lr"},{"id":"2608.08239","title":"The Replay Gap: Static Evaluation of Model Switching in LLM Agents Scores the Wrong World","created":"2026-08-08","cited_by_count":8,"area":"agents"},{"id":"2509.21837","title":"Semantic Agreement Enables Efficient Open-Ended LLM Cascades","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2510.00841","title":"LLM Routing with Dueling Feedback","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2602.03584","title":"$V_0$: A Generalist Value Model for Any Policy at State Zero","created":"2026-02-03","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":"2603.07892","title":"RoboRouter: Training-Free Policy Routing for Robotic Manipulation","created":"2026-03-09","cited_by_count":6,"area":"vla"},{"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":"2510.10988","title":"Adversarial Robustness in One-Stage Learning-to-Defer","created":"2025-10-13","cited_by_count":5,"area":null},{"id":"2608.16721","title":"GenRouter: Unified Workflow Routing for Agentic Image Generation","created":"2026-08-17","cited_by_count":5,"area":"agents"},{"id":"2506.14753","title":"Cost-Aware Routing for Efficient Text-To-Image Generation","created":"2025-06-17","cited_by_count":4,"area":"diffusion"},{"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":"2511.02130","title":"Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning","created":"2025-11-03","cited_by_count":4,"area":"lr"},{"id":"2601.09692","title":"Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection","created":"2026-01-14","cited_by_count":4,"area":null},{"id":"2601.11589","title":"LAPS: A Length-Aware-Prefill LLM Serving System","created":"2026-01-04","cited_by_count":4,"area":"inference"},{"id":"2602.22124","title":"SWE-Prot\\'eg\\'e: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents","created":"2026-02-25","cited_by_count":4,"area":"agents"},{"id":"2603.22206","title":"Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs","created":"2026-03-23","cited_by_count":4,"area":"agents"},{"id":"2506.17254","title":"Near-Optimal Online Deployment and Routing for Streaming LLMs","created":"2025-06-08","cited_by_count":3,"area":null},{"id":"2601.04544","title":"TCAndon-Router: Adaptive Reasoning Router for Multi-Agent Collaboration","created":"2026-01-08","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":"2602.17144","title":"When More Experts Hurt: Underfitting in Multi-Expert Learning to Defer","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2603.03761","title":"AgentSelect: Benchmark for Narrative Query-to-Agent Recommendation","created":"2026-03-04","cited_by_count":3,"area":"agents"},{"id":"2603.26796","title":"Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity Constraints","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2605.07112","title":"Switchcraft: AI Model Router for Agentic Tool Calling","created":"2026-05-08","cited_by_count":3,"area":"agents"},{"id":"2605.07180","title":"Learning Agent Routing From Early Experience","created":"2026-05-08","cited_by_count":3,"area":"agents"},{"id":"2504.07247","title":"Resource-efficient Inference with Foundation Model Programs","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2602.02711","title":"Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.04101","title":"Interfaze: The Future of AI is built on Task-Specific Small Models","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2603.07705","title":"Deep Incentive Design with Differentiable Equilibrium Blocks","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2608.20316","title":"Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation","created":"2026-08-20","cited_by_count":2,"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":"2604.15728","title":"Privacy-Preserving LLMs Routing","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2605.14241","title":"Latency-Quality Routing for Functionally Equivalent Tools in LLM Agents","created":"2026-05-14","cited_by_count":1,"area":"agents"},{"id":"2605.22057","title":"FlyRoute: Self-Evolving Agent Profiling via Data Flywheel for Adaptive Task Routing","created":"2026-05-21","cited_by_count":1,"area":"agents"},{"id":"2605.30102","title":"When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems","created":"2026-05-28","cited_by_count":1,"area":"agents"},{"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":"2606.14929","title":"Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2606.17949","title":"RouteBalance: Fused Model Routing and Load Balancing for Heterogeneous LLM Serving","created":"2026-06-16","cited_by_count":1,"area":"inference"},{"id":"2606.20138","title":"Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoring","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2606.26836","title":"The Capability Frontier: Benchmarks Miss 82% of Model Performance","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2607.06145","title":"Prompting Complexity: Shortest Prompts for Texts and Behaviors in LLMs","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2607.18098","title":"VDAR-Router: Adaptive LLMs Routing via Verbalized Query Difficulty Analysis Retrieval","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2607.18253","title":"Mind the Delay: Latency-aware Query Routing for Heterogeneous LLM pools","created":"2026-05-13","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":"2608.07583","title":"RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2609.34712","title":"RSI-Router: Evolving Subtask-Level LLM Routing and Skills for Cost-Efficient Agents","created":"2026-09-28","cited_by_count":1,"area":"agents"},{"id":"2610.02762","title":"Dynamic LLM Routers are Often Misguided","created":"2026-10-02","cited_by_count":1,"area":null},{"id":"2507.14200","title":"A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2507.22937","title":"CoE-Ops: Collaboration of LLM-based Experts for AIOps Question-Answering","created":"2025-07-25","cited_by_count":0,"area":"moe"},{"id":"2512.22402","title":"Efficient Multi-Model Orchestration for Self-Hosted Large Language Models","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2602.04856","title":"CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation","created":"2026-02-04","cited_by_count":0,"area":"lr"},{"id":"2603.05175","title":"Incentive Aware AI Regulations: A Credal Characterisation","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.15647","title":"Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing","created":"2026-03-04","cited_by_count":0,"area":"alignment"},{"id":"2603.24787","title":"ReLope: KL-Regularized LoRA Probes for Multimodal LLM Routing","created":"2026-03-25","cited_by_count":0,"area":"mllm"},{"id":"2605.07171","title":"Cost-Ordered Feasibility for Multi-Armed Bandits with Cost Subsidy","created":"2026-05-08","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":"2606.06098","title":"IR3DE: A Linear Router for Large Language Models","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.07711","title":"Rosetta Memory: Adaptive Memory for Cross-LLM Agents","created":"2026-06-05","cited_by_count":0,"area":"agents"},{"id":"2606.27457","title":"Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving","created":"2026-06-25","cited_by_count":0,"area":"inference"},{"id":"2607.22561","title":"Codifying the Judge: Scalable Evaluation via Program Distillation","created":"2026-05-29","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":"2609.23085","title":"Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving","created":"2026-09-19","cited_by_count":0,"area":"lr"},{"id":"2609.34326","title":"Routing Without Embeddings: Fast And Interpretable Routing With Regular Expressions","created":"2026-09-28","cited_by_count":0,"area":"mechinterp"},{"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":"2610.06216","title":"Cross-lingual Calibration of Pre-Generation Success Probes for Multilingual LLM Routing","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.18566","title":"Rethinking Quality in Large Language Model Routing: Security-Conditioned Model-and-Budget Selection","created":"2026-10-13","cited_by_count":0,"area":"lr"},{"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},{"id":"2610.19292","title":"Whose turn is it? Context-guided model routing for stateful agents","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.20587","title":"Price of Anarchy of First-Price Auctions in Agentic Markets","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}