{"total":143,"rows":[{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238,"area":null},{"id":"2311.17311","title":"Universal Self-Consistency for Large Language Model Generation","created":"2023-11-29","cited_by_count":203,"area":"lr"},{"id":"2503.05179","title":"Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching","created":"2025-03-07","cited_by_count":117,"area":"lr"},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2402.18659","title":"Large Language Models and Games: A Survey and Roadmap","created":"2024-02-28","cited_by_count":93,"area":null},{"id":"2409.19886","title":"RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models","created":"2024-09-30","cited_by_count":88,"area":null},{"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":"2410.13284","title":"Learning to Route LLMs with Confidence Tokens","created":"2024-10-17","cited_by_count":67,"area":null},{"id":"2506.22716","title":"BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute","created":"2025-06-28","cited_by_count":67,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"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":"2506.10805","title":"Detecting High-Stakes Interactions with Activation Probes","created":"2025-06-12","cited_by_count":53,"area":null},{"id":"2601.11516","title":"Building Production-Ready Probes For Gemini","created":"2026-01-16","cited_by_count":47,"area":"safety"},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44,"area":null},{"id":"2502.03261","title":"CARROT: A Cost Aware Rate Optimal Router","created":"2025-02-05","cited_by_count":39,"area":null},{"id":"2405.19261","title":"Faster Cascades via Speculative Decoding","created":"2024-05-29","cited_by_count":38,"area":"inference"},{"id":"2407.14414","title":"System-1.x: Learning to Balance Fast and Slow Planning with Language Models","created":"2024-07-19","cited_by_count":35,"area":null},{"id":"2412.03324","title":"A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs","created":"2024-12-04","cited_by_count":35,"area":"mllm"},{"id":"2407.11418","title":"Semantic Operators: A Declarative Model for Rich, AI-based Data Processing","created":"2024-07-16","cited_by_count":34,"area":null},{"id":"2405.02134","title":"Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selection","created":"2024-05-03","cited_by_count":33,"area":null},{"id":"2502.04506","title":"When One LLM Drools, Multi-LLM Collaboration Rules","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2402.11406","title":"Don't Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection","created":"2024-02-18","cited_by_count":25,"area":null},{"id":"2410.03524","title":"Steering Large Language Models between Code Execution and Textual Reasoning","created":"2024-10-04","cited_by_count":24,"area":"lr"},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2407.02056","title":"Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation","created":"2024-07-02","cited_by_count":21,"area":"lr"},{"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":"2505.15817","title":"Learning to Reason via Mixture-of-Thought for Logical Reasoning","created":"2025-05-21","cited_by_count":20,"area":"lr"},{"id":"2312.10730","title":"Mixed Distillation Helps Smaller Language Model Better Reasoning","created":"2023-12-17","cited_by_count":19,"area":"lr"},{"id":"2411.07464","title":"BudgetMLAgent: A Cost-Effective LLM Multi-Agent system for Automating Machine Learning Tasks","created":"2024-11-12","cited_by_count":19,"area":"agents"},{"id":"2601.06123","title":"Latent Space Communication via K-V Cache Alignment","created":"2026-01-04","cited_by_count":17,"area":null},{"id":"2407.02348","title":"Agreement-Based Cascading for Efficient Inference","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2508.12491","title":"Cost-Aware Contrastive Routing for LLMs","created":"2025-08-17","cited_by_count":16,"area":null},{"id":"2509.26238","title":"Beyond Linear Probes: Dynamic Safety Monitoring for Language Models","created":"2025-09-30","cited_by_count":16,"area":"safety"},{"id":"2406.00060","title":"Cascade-Aware Training of Language Models","created":"2024-05-29","cited_by_count":15,"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":"2410.18779","title":"A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2407.01965","title":"AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment","created":"2024-07-02","cited_by_count":14,"area":null},{"id":"2502.09054","title":"Cost-Saving LLM Cascades with Early Abstention","created":"2025-02-13","cited_by_count":14,"area":null},{"id":"2402.02563","title":"Synergy-of-Thoughts: Eliciting Efficient Reasoning in Hybrid Language Models","created":"2024-02-04","cited_by_count":13,"area":"lr"},{"id":"2410.16676","title":"CausalEval: Towards Better Causal Reasoning in Language Models","created":"2024-10-22","cited_by_count":13,"area":"lr"},{"id":"2412.12170","title":"PickLLM: Context-Aware RL-Assisted Large Language Model Routing","created":"2024-12-12","cited_by_count":13,"area":null},{"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":"2506.00911","title":"Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models","created":"2025-06-01","cited_by_count":12,"area":null},{"id":"2506.03880","title":"RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing","created":"2025-06-04","cited_by_count":11,"area":null},{"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":"2501.09345","title":"Rational Tuning of LLM Cascades via Probabilistic Modeling","created":"2025-01-16","cited_by_count":10,"area":null},{"id":"2502.19335","title":"Gatekeeper: Improving Model Cascades Through Confidence Tuning","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2510.09913","title":"Don't Throw Away Your Pretrained Model","created":"2025-10-10","cited_by_count":10,"area":"lr"},{"id":"2402.02053","title":"Affordable Generative Agents","created":"2024-02-03","cited_by_count":9,"area":"agents"},{"id":"2402.12146","title":"Enabling Weak LLMs to Judge Response Reliability via Meta Ranking","created":"2024-02-19","cited_by_count":9,"area":null},{"id":"2503.13505","title":"Ensemble Learning for Large Language Models in Text and Code Generation: A Survey","created":"2025-03-13","cited_by_count":9,"area":null},{"id":"2506.12473","title":"TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks","created":"2025-06-14","cited_by_count":9,"area":null},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2407.09502","title":"From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models","created":"2024-06-14","cited_by_count":8,"area":null},{"id":"2410.08014","title":"Privacy-preserved LLM Cascade via CoT-enhanced Policy Learning","created":"2024-10-10","cited_by_count":8,"area":null},{"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":"2512.22309","title":"LLMBoost: Make Large Language Models Stronger with Boosting","created":"2025-12-26","cited_by_count":8,"area":null},{"id":"2506.11578","title":"Efficient LLM Collaboration via Planning","created":"2025-06-13","cited_by_count":7,"area":"lr"},{"id":"2509.21837","title":"Semantic Agreement Enables Efficient Open-Ended LLM Cascades","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2510.01394","title":"Optimal Stopping vs Best-of-$N$ for Inference Time Optimization","created":"2025-10-01","cited_by_count":7,"area":"alignment"},{"id":"2510.05164","title":"SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascading","created":"2025-10-04","cited_by_count":7,"area":null},{"id":"2510.13890","title":"A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2604.07036","title":"ReDAct: Uncertainty-Aware Deferral for LLM Agents","created":"2026-04-08","cited_by_count":7,"area":"agents"},{"id":"2605.15206","title":"AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices","created":"2026-05-01","cited_by_count":6,"area":"agents"},{"id":"2608.24358","title":"The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents","created":"2026-08-25","cited_by_count":6,"area":"agents"},{"id":"2405.15842","title":"Model Cascading for Code: A Cascaded Black-Box Multi-Model Framework for Cost-Efficient Code Completion with Self-Testing","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2410.02173","title":"Efficiently Deploying LLMs with Controlled Risk","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2506.03857","title":"Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation","created":"2025-06-04","cited_by_count":5,"area":"distill"},{"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":"2510.07768","title":"ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning","created":"2025-10-09","cited_by_count":5,"area":"lr"},{"id":"2502.01459","title":"Learning to Partially Defer for Sequences","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2511.16964","title":"Optimizing PyTorch Inference with LLM-Based Multi-Agent Systems","created":"2025-11-21","cited_by_count":4,"area":"agents"},{"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":"2402.10866","title":"EcoRank: Budget-Constrained Text Re-ranking Using Large Language Models","created":"2024-02-16","cited_by_count":3,"area":null},{"id":"2503.16575","title":"Extract, Match, and Score: An Evaluation Paradigm for Long Question-context-answer Triplets in Financial Analysis","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2506.10525","title":"AdaptiveLLM: A Framework for Selecting Optimal Cost-Efficient LLM for Code-Generation Based on CoT Length","created":"2025-06-12","cited_by_count":3,"area":"lr"},{"id":"2506.15733","title":"$\\texttt{SPECS}$: Faster Test-Time Scaling through Speculative Drafts","created":"2025-06-15","cited_by_count":3,"area":"lr"},{"id":"2506.17254","title":"Near-Optimal Online Deployment and Routing for Streaming LLMs","created":"2025-06-08","cited_by_count":3,"area":null},{"id":"2509.21091","title":"Best-of-$\\infty$ -- Asymptotic Performance of Test-Time LLM Ensembling","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2510.03930","title":"LLM Chemistry Estimation for Multi-LLM Recommendation","created":"2025-10-04","cited_by_count":3,"area":null},{"id":"2601.18130","title":"RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents","created":"2026-01-26","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":"2606.06924","title":"From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing","created":"2026-06-05","cited_by_count":3,"area":"lr"},{"id":"2607.23765","title":"WISERouter: LLM Routing with Workload Budget Constraint","created":"2026-07-26","cited_by_count":3,"area":null},{"id":"2403.13835","title":"SMART: Automatically Scaling Down Language Models with Accuracy Guarantees for Reduced Processing Fees","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2404.15153","title":"Performance Characterization of Expert Router for Scalable LLM Inference","created":"2024-04-22","cited_by_count":2,"area":null},{"id":"2411.13787","title":"Adaptive Routing of Text-to-Image Generation Requests Between Large Cloud Model and Light-Weight Edge Model","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2504.15300","title":"Collaborative Learning of On-Device Small Model and Cloud-Based Large Model: Advances and Future Directions","created":"2025-04-17","cited_by_count":2,"area":null},{"id":"2504.19391","title":"Bi-directional Model Cascading with Proxy Confidence","created":"2025-04-27","cited_by_count":2,"area":null},{"id":"2508.03329","title":"Industrial LLM-based Code Optimization under Regulation: A Mixture-of-Agents Approach","created":"2025-08-05","cited_by_count":2,"area":"agents"},{"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":"2512.05066","title":"Multi-LLM Collaboration for Medication Recommendation","created":"2025-12-04","cited_by_count":2,"area":null},{"id":"2602.05182","title":"The Single-Multi Evolution Loop for Self-Improving Model Collaboration Systems","created":"2026-02-05","cited_by_count":2,"area":"synth"},{"id":"2602.05307","title":"MentorCollab: Large-to-Small Inference-Time Mentorship for Concise Reasoning in Language Models","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2602.09902","title":"Routing, Cascades, and User Choice for LLMs","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2602.14901","title":"Picking the Right Specialist: Attentive Neural Process-based Selection of Task-Specialized Models as Tools for Agentic Healthcare Systems","created":"2026-02-16","cited_by_count":2,"area":"agents"},{"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":"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":"2607.26865","title":"Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents","created":"2026-07-29","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}