{"total":88,"rows":[{"id":"2502.08773","title":"Universal Model Routing for Efficient LLM Inference","created":"2025-02-12","cited_by_count":86,"area":"inference"},{"id":"2503.09501","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","created":"2025-03-12","cited_by_count":79,"area":"lr"},{"id":"2506.09033","title":"Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning","created":"2025-06-10","cited_by_count":72,"area":null},{"id":"2504.00255","title":"SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers","created":"2025-03-31","cited_by_count":43,"area":"agents"},{"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":"2502.20576","title":"OmniRouter: Budget and Performance Controllable Multi-LLM Routing","created":"2025-02-27","cited_by_count":35,"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":"2502.14855","title":"Prompt-to-Leaderboard","created":"2025-02-20","cited_by_count":30,"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":"2512.04388","title":"Learning to Orchestrate Agents in Natural Language with the Conductor","created":"2025-12-04","cited_by_count":23,"area":"agents"},{"id":"2602.19672","title":"SkillOrchestra: Learning to Route Agents via Skill Transfer","created":"2026-02-23","cited_by_count":23,"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":"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":"2410.15761","title":"Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees","created":"2024-10-21","cited_by_count":15,"area":null},{"id":"2503.01155","title":"Nature-Inspired Population-Based Evolution of Large Language Models","created":"2025-03-03","cited_by_count":15,"area":null},{"id":"2510.07429","title":"Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offs","created":"2025-10-08","cited_by_count":15,"area":null},{"id":"2604.05149","title":"EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering","created":"2026-04-06","cited_by_count":15,"area":"agents"},{"id":"2511.07885","title":"Intelligence per Watt: Measuring Intelligence Efficiency of Local AI","created":"2025-11-11","cited_by_count":14,"area":null},{"id":"2503.22402","title":"EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routing","created":"2025-03-28","cited_by_count":13,"area":null},{"id":"2506.05901","title":"Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router","created":"2025-06-06","cited_by_count":13,"area":"lr"},{"id":"2601.17814","title":"MMR-Bench: A Comprehensive Benchmark for Multimodal LLM Routing","created":"2026-01-25","cited_by_count":13,"area":"mllm"},{"id":"2503.08704","title":"Life-Cycle Routing Vulnerabilities of LLM Router","created":"2025-03-09","cited_by_count":11,"area":"safety"},{"id":"2505.12601","title":"Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers","created":"2025-05-19","cited_by_count":11,"area":"lr"},{"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":"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":"2506.16655","title":"Arch-Router: Aligning LLM Routing with Human Preferences","created":"2025-06-19","cited_by_count":9,"area":"alignment"},{"id":"2602.01064","title":"Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMs","created":"2026-02-01","cited_by_count":9,"area":"distill"},{"id":"2603.07972","title":"Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning","created":"2026-03-09","cited_by_count":9,"area":"agents"},{"id":"2503.00481","title":"Challenges in Testing Large Language Model Based Software: A Faceted Taxonomy","created":"2025-03-01","cited_by_count":8,"area":"agents"},{"id":"2505.23052","title":"RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models","created":"2025-05-29","cited_by_count":8,"area":"rag"},{"id":"2510.07835","title":"MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation","created":"2025-10-09","cited_by_count":8,"area":"safety"},{"id":"2512.23562","title":"VL-RouterBench: A Benchmark for Vision-Language Model Routing","created":"2025-12-29","cited_by_count":8,"area":"mllm"},{"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":"2501.07813","title":"Talk to Right Specialists: Iterative Routing in Multi-agent Systems for Question Answering","created":"2025-01-14","cited_by_count":6,"area":"rag"},{"id":"2510.05077","title":"Slm-mux: Orchestrating small language models for reasoning","created":"2025-10-06","cited_by_count":6,"area":"lr"},{"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":"2602.00296","title":"RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing","created":"2026-01-30","cited_by_count":6,"area":"rag"},{"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":"2605.05007","title":"Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation","created":"2026-05-06","cited_by_count":6,"area":"agents"},{"id":"2512.04695","title":"TRINITY: An Evolved LLM Coordinator","created":"2025-12-04","cited_by_count":5,"area":null},{"id":"2511.16883","title":"PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling","created":"2025-11-21","cited_by_count":4,"area":null},{"id":"2603.03336","title":"Prompt-Dependent Ranking of Large Language Models with Uncertainty Quantification","created":"2026-02-11","cited_by_count":4,"area":"alignment"},{"id":"2606.21228","title":"Sakana Fugu Technical Report","created":"2026-06-19","cited_by_count":4,"area":"agents"},{"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":"2506.17254","title":"Near-Optimal Online Deployment and Routing for Streaming LLMs","created":"2025-06-08","cited_by_count":3,"area":null},{"id":"2509.07571","title":"Towards Generalized Routing: Model and Agent Orchestration for Adaptive and Efficient Inference","created":"2025-09-09","cited_by_count":3,"area":"agents"},{"id":"2510.24031","title":"LLMLogAnalyzer: A Clustering-Based Log Analysis Chatbot using Large Language Models","created":"2025-10-28","cited_by_count":3,"area":null},{"id":"2603.12933","title":"Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization","created":"2026-03-13","cited_by_count":3,"area":"agents"},{"id":"2605.07112","title":"Switchcraft: AI Model Router for Agentic Tool Calling","created":"2026-05-08","cited_by_count":3,"area":"agents"},{"id":"2605.18067","title":"PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligence","created":"2026-05-18","cited_by_count":3,"area":"agents"},{"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":"2505.14524","title":"Guarded Query Routing for Large Language Models","created":"2025-05-20","cited_by_count":2,"area":"safety"},{"id":"2510.11221","title":"WebRouter: Query-specific Router via Variational Information Bottleneck for Cost-sensitive Web Agent","created":"2025-10-13","cited_by_count":2,"area":"agents"},{"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":"2604.02319","title":"No Single Best Model for Diversity: Learning a Router for Sample Diversity","created":"2026-04-02","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":"2605.11301","title":"LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2606.09668","title":"Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2607.08940","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2607.14277","title":"Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making","created":"2026-07-15","cited_by_count":2,"area":"agents"},{"id":"2512.09386","title":"CONCUR: A Framework for Continual Constrained and Unconstrained Routing","created":"2025-12-10","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":"2605.12001","title":"CR^2: Cost-Aware Risk-Controlled Routing for Wireless Device-Edge LLM Inference","created":"2026-05-12","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":"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":"2609.38585","title":"FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2510.27051","title":"Adaptive Data Flywheel: Applying MAPE Control Loops to AI Agent Improvement","created":"2025-10-30","cited_by_count":0,"area":"moe"},{"id":"2603.30035","title":"Reward-Based Online LLM Routing via NeuralUCB","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.06339","title":"A Regime Theory of Controller Class Selection for LLM Action Decisions","created":"2026-05-07","cited_by_count":0,"area":"mllm"},{"id":"2605.08686","title":"Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs","created":"2026-05-09","cited_by_count":0,"area":"agents"},{"id":"2605.10384","title":"Agentic Performance at the Edge: Insights from Benchmarking","created":"2026-05-11","cited_by_count":0,"area":"agents"},{"id":"2605.28030","title":"SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2606.15872","title":"SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks","created":"2026-06-14","cited_by_count":0,"area":"lr"},{"id":"2607.04389","title":"Decentralized Aggregation of LLM Predictions via Wagering Mechanisms","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2608.01885","title":"CARE: A Cascaded Framework for Efficient and Reliable Time Series Anomaly Detection","created":"2026-08-03","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":"2608.15817","title":"RLCascadeRouter: Quality-Estimator-Free Cascade Routing via Reinforcement Learning","created":"2026-08-16","cited_by_count":0,"area":"lr"},{"id":"2608.16375","title":"Multinomial Subset Routing with Sum-Max Rewards and Operational Constraints","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.13470","title":"OrchSLM: Probing the Dynamics of Small Language Model Orchestration","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.34736","title":"SeLMRoute: Probabilistic Semantic Evidence for Large Language Model Routing","created":"2026-09-28","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":"2610.05896","title":"TasteRoute: Personalized Routing for Video Generation","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},{"id":"2610.18354","title":"Choosing LLMs for Strategic Agent Interactions","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.19705","title":"RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}