{"total":80,"rows":[{"id":"2502.08773","title":"Universal Model Routing for Efficient LLM Inference","created":"2025-02-12","cited_by_count":86,"area":"inference"},{"id":"2502.18036","title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","created":"2025-02-25","cited_by_count":86,"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":"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":"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":"2606.27288","title":"When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models","created":"2026-06-25","cited_by_count":13,"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":"2511.07396","title":"C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning","created":"2025-11-10","cited_by_count":8,"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":"2511.21572","title":"BAMAS: Structuring Budget-Aware Multi-Agent Systems","created":"2025-11-26","cited_by_count":6,"area":"agents"},{"id":"2603.09018","title":"Meissa: Multi-modal Medical Agentic Intelligence","created":"2026-03-09","cited_by_count":6,"area":"mllm"},{"id":"2506.04203","title":"Cascadia: An Efficient Cascade Serving System for Large Language Models","created":"2025-06-04","cited_by_count":5,"area":"inference"},{"id":"2511.08590","title":"GMTRouter: Personalized LLM Router over Multi-turn User Interactions","created":"2025-10-29","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":"2605.06350","title":"Is Escalation Worth It? On the Depth of LLM Cascades","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2510.03930","title":"LLM Chemistry Estimation for Multi-LLM Recommendation","created":"2025-10-04","cited_by_count":3,"area":null},{"id":"2512.03057","title":"A note on conditional PAC-efficient reasoning in large language model routing","created":"2025-11-25","cited_by_count":3,"area":"lr"},{"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":"2604.03527","title":"Explainable Model Routing for Agentic Workflows","created":"2026-04-04","cited_by_count":3,"area":"agents"},{"id":"2604.12262","title":"CascadeDebate: Multi-Agent Deliberation for Cost-Aware LLM Cascades","created":"2026-04-14","cited_by_count":3,"area":"agents"},{"id":"2604.14251","title":"Calibrate-Then-Delegate: Safety Monitoring with Risk and Budget Guarantees via Model Cascades","created":"2026-04-15","cited_by_count":3,"area":"safety"},{"id":"2606.04883","title":"Optimizing the Cost-Quality Tradeoff of Agentic Theorem Provers in Lean","created":"2026-06-03","cited_by_count":3,"area":"agents"},{"id":"2607.19338","title":"CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents","created":"2026-07-21","cited_by_count":3,"area":"agents"},{"id":"2607.23765","title":"WISERouter: LLM Routing with Workload Budget Constraint","created":"2026-07-26","cited_by_count":3,"area":null},{"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":"2602.09902","title":"Routing, Cascades, and User Choice for LLMs","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2603.27299","title":"From Inference Routing to Agent Orchestration: Declarative Policy Compilation with Cross-Layer Verification","created":"2026-03-28","cited_by_count":2,"area":"agents"},{"id":"2604.23577","title":"RouteNLP: Closed-Loop LLM Routing with Conformal Cascading and Distillation Co-Optimization","created":"2026-04-26","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":"2605.16604","title":"R2V Agent: Teaching SLMs When to Ask for Help","created":"2026-05-15","cited_by_count":2,"area":"agents"},{"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":"2608.02528","title":"Uncertainty Is Not Enough: Value-of-Information Routing for Mixtures of LoRA Experts","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2601.22446","title":"Anytime Safe PAC Efficient Reasoning","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.02550","title":"HyPAC: Cost-Efficient LLMs-Human Hybrid Annotation with PAC Error Guarantees","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2603.24617","title":"Multi-LLM Query Optimization","created":"2026-03-24","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":"2607.08665","title":"Resample or Reroute? Recoverable Stopping Debt Without Identified Action Selection","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2607.15516","title":"Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching","created":"2026-07-17","cited_by_count":1,"area":"inference"},{"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":"2608.10333","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":"2608.22215","title":"Dual-Layer Agentic Memory with Fast Write Routing and Slow Consolidation","created":"2026-08-23","cited_by_count":1,"area":"agents"},{"id":"2609.00662","title":"Drift-Aware LLM Routing with Sparse Contexts and Shared Budgets","created":"2026-09-01","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":"2504.10681","title":"EMAFusion: A Self-Optimizing System for Seamless LLM Selection and Integration","created":"2025-04-14","cited_by_count":0,"area":null},{"id":"2509.22992","title":"T-TAMER: Provably Taming Trade-offs in ML Serving","created":"2025-09-26","cited_by_count":0,"area":"inference"},{"id":"2510.08365","title":"Two-Stage Voting for Robust and Efficient Suicide Risk Detection on Social Media","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2603.23013","title":"Knowledge Access Beats Model Size: Memory Augmented Routing for Persistent AI Agents","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2603.27571","title":"RAGent: Physics-Aware Agentic Reasoning for Training-Free mmWave Human Activity Recognition","created":"2026-03-29","cited_by_count":0,"area":"lr"},{"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":"2605.07805","title":"Flexible Routing via Uncertainty Decomposition","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.23914","title":"VineLM: Trie-Based Fine-Grained Control for Agentic Workflows","created":"2026-04-09","cited_by_count":0,"area":"agents"},{"id":"2606.06098","title":"IR3DE: A Linear Router for Large Language Models","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.20713","title":"FairTutor: Equity-Aware Pedagogical LLM Routing for Budget-Constrained AI Tutoring","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.25871","title":"AutoRelAnnotator: Calibrated Model Cascades for Cost-Efficient Relevance Evaluation in Sponsored Search","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.13239","title":"Cost-Optimal Foundation Model Deployment Portfolio for Transportation Management","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.24801","title":"Influence of Prompt Engineering on Small Language Models for Guarded Query Routing","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.10362","title":"MemSpec: Memory-Aware Runtime for Adaptive Draft Scheduling in Speculative Decoding on Edge Devices","created":"2026-08-11","cited_by_count":0,"area":"inference"},{"id":"2608.10441","title":"Detecting an Effect Is Not Learning to Act on It: A Reward-SNR Floor for LLM Acquisition Agents","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.15817","title":"RLCascadeRouter: Quality-Estimator-Free Cascade Routing via Reinforcement Learning","created":"2026-08-16","cited_by_count":0,"area":"lr"},{"id":"2609.02292","title":"SCX Router: Streaming Zero-Shot Model Selection with a Decoder-KV Classifier and a Real-World Task Ontology","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.11446","title":"Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.17977","title":"When to Call an LLM: A Confidence-Gated Hybrid for Cost-Effective Emotion Recognition in Conversational AI","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.26913","title":"COMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.27869","title":"Learning What to Activate: Combinatorial Capability Allocation for Long-Horizon Multimodal Agents","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.38274","title":"Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.01110","title":"How Much Can Language Models Gain from Test-Time Computation?","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01535","title":"False Floors: LLM Safety Routing Evaluations Break Under Distribution Shift","created":"2026-10-01","cited_by_count":0,"area":null},{"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":"2610.06216","title":"Cross-lingual Calibration of Pre-Generation Success Probes for Multilingual LLM Routing","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.07716","title":"Readout Stability in Prefill-Only Decision Models:Zero-Label Prediction and Inference-Time Compute Allocation","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.12927","title":"Collaborative Learning and Reasoning over Model Slices","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.13276","title":"CopRoute: Dependence-Aware Conformal Routing for Language Models","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14688","title":"Accelerating Cross-Model LLM Inference via Attention Map Reuse","created":"2026-10-10","cited_by_count":0,"area":"inference"},{"id":"2610.14886","title":"Agent-Guided Evidence Acquisition for Emotion-Cause Pair Extraction","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.19292","title":"Whose turn is it? Context-guided model routing for stateful agents","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}