{"total":72,"rows":[{"id":"2508.02120","title":"Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models","created":"2025-08-04","cited_by_count":37,"area":"lr"},{"id":"2601.14652","title":"MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks","created":"2026-01-21","cited_by_count":32,"area":null},{"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":"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":"2510.08439","title":"xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning","created":"2025-10-09","cited_by_count":17,"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":"2602.06025","title":"Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory","created":"2026-02-05","cited_by_count":13,"area":"agents"},{"id":"2604.23626","title":"GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs","created":"2026-04-26","cited_by_count":12,"area":"agents"},{"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":"2602.21227","title":"Budget-Aware Agentic Routing via Boundary-Guided Training","created":"2026-02-04","cited_by_count":10,"area":"agents"},{"id":"2602.01202","title":"Workflow-R1: Group Sub-sequence Policy Optimization for Multi-turn Workflow Construction","created":"2026-02-01","cited_by_count":8,"area":"agents"},{"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":"2603.06616","title":"RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models","created":"2026-02-20","cited_by_count":7,"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":"2605.05007","title":"Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation","created":"2026-05-06","cited_by_count":6,"area":"agents"},{"id":"2509.24050","title":"Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training","created":"2025-09-28","cited_by_count":5,"area":"lr"},{"id":"2510.10009","title":"Beyond the limitation of a single query: Train your LLM for query expansion with Reinforcement Learning","created":"2025-10-11","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":"2511.16883","title":"PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling","created":"2025-11-21","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":"2601.22323","title":"Models Under SCOPE: Scalable and Controllable Routing via Pre-hoc Reasoning","created":"2026-01-29","cited_by_count":4,"area":"lr"},{"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":"2604.05164","title":"Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning in Agents","created":"2026-04-06","cited_by_count":4,"area":"lr"},{"id":"2604.12385","title":"From Myopic Selection to Long-Horizon Awareness: Sequential LLM Routing for Multi-Turn Dialogue","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2606.01667","title":"ATLAS: Agentic Test-time Learning-to-Allocate Scaling","created":"2026-06-01","cited_by_count":4,"area":"lr"},{"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":"2512.23340","title":"The Law of Multi-Model Collaboration: Scaling Limits of Model Ensembling for Large Language Models","created":"2025-12-29","cited_by_count":3,"area":null},{"id":"2601.21414","title":"System 1&2 Synergy via Dynamic Model Interpolation","created":"2026-01-29","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":"2605.07180","title":"Learning Agent Routing From Early Experience","created":"2026-05-08","cited_by_count":3,"area":"agents"},{"id":"2606.26122","title":"DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents","created":"2026-05-27","cited_by_count":3,"area":"agents"},{"id":"2510.08872","title":"GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfare","created":"2025-10-10","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":"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":"2605.25424","title":"SeqRoute: Global Budget-Aware Sequential LLM Routing via Offline Reinforcement Learning","created":"2026-05-25","cited_by_count":2,"area":"offlinerl"},{"id":"2606.13598","title":"Reward Modeling for Multi-Agent Orchestration","created":"2026-06-11","cited_by_count":2,"area":"lr"},{"id":"2607.08940","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2608.23867","title":"Markets, Not Planners: Decentralized Orchestration of LLM Agents with Private Information","created":"2026-08-24","cited_by_count":2,"area":"agents"},{"id":"2602.18990","title":"IDSelect: A RL-Based Cost-Aware Selection Agent for Video-based Multi-Modal Person Recognition","created":"2026-02-22","cited_by_count":1,"area":"deeprl"},{"id":"2603.21354","title":"The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project","created":"2026-03-22","cited_by_count":1,"area":"agents"},{"id":"2603.26557","title":"MemBoost: A Memory-Boosted Framework for Cost-Aware LLM Inference","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2603.26728","title":"SEAR: Schema-Based Evaluation and Routing for LLM Gateways","created":"2026-03-20","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":"2604.22436","title":"AgentSearchBench: A Benchmark for AI Agent Search in the Wild","created":"2026-04-24","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":"2606.07587","title":"The Routing Plateau: Understanding the Accuracy Limits of LLM Routers","created":"2026-05-27","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":"2608.10333","title":"MERA: Model Evolution and Routing with Skill Adaptation for Agentic Systems at Scale","created":"2026-08-11","cited_by_count":1,"area":"agents"},{"id":"2608.12719","title":"Error-Aware Reverse Auction Mechanism for Large Language Model Routing","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2609.34247","title":"SALMONN-duo: Adaptive Dual-System Coordination for Full-Duplex Voice Agents","created":"2026-09-28","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":"2602.09173","title":"$n$-Musketeers: Reinforcement Learning Shapes Collaboration Among Language Models","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2604.06296","title":"AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent","created":"2026-04-07","cited_by_count":0,"area":"agents"},{"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":"2607.29087","title":"Harnessing the Wisdom of LLM Crowds through Complementarity-Driven Iterative Collaboration","created":"2026-07-31","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":"2608.20927","title":"MentorPulse: Refreshing Cross-Model Latent Guidance for Long-Form Generation","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.29560","title":"Which LLM for Which Work? Budgeted Model Allocation under Uncertain Evaluation","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.12578","title":"From Collaboration to Capability: Internalizing Routed LLM Experts into Compact Reasoners","created":"2026-09-11","cited_by_count":0,"area":"lr"},{"id":"2609.25047","title":"AIBuildAI-2.5: Efficient Autonomous AI Model Development Through LLM-Guided Tree Search","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.30270","title":"HybridInfer: Thermal-Aware Reinforcement-Learning Tier Routing for On-Device, Edge, and Cloud LLM Inference","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2609.39777","title":"GraphMAS: A Systematic Benchmark of Multi-Agent Coordination for Graph Learning","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"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":"2610.05896","title":"TasteRoute: Personalized Routing for Video Generation","created":"2026-10-05","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":"2610.14886","title":"Agent-Guided Evidence Acquisition for Emotion-Cause Pair Extraction","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.17456","title":"Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.17816","title":"Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.19458","title":"PFedMA: Who Should Join Next as Federated Multi-Agent Orchestration Evolves?","created":"2026-10-14","cited_by_count":0,"area":"lr"},{"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}