{"list":"other","total":92,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2009.09025","title":"COMET: A Neural Framework for MT Evaluation","created":"2020-09-18","cited_by_count":1033},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"2306.02561","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","created":"2023-06-05","cited_by_count":564},{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2302.09210","title":"How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation","created":"2023-02-18","cited_by_count":348},{"id":"2409.12183","title":"To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning","created":"2024-09-18","cited_by_count":263},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238},{"id":"1906.04908","title":"SPoC: Search-based Pseudocode to Code","created":"2019-06-12","cited_by_count":176},{"id":"2309.15789","title":"Large Language Model Routing with Benchmark Datasets","created":"2023-09-27","cited_by_count":172},{"id":"2410.03834","title":"GraphRouter: A Graph-based Router for LLM Selections","created":"2024-10-04","cited_by_count":165},{"id":"2503.04472","title":"DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models","created":"2025-03-06","cited_by_count":158},{"id":"2505.13417","title":"AdaptThink: Reasoning Models Can Learn When to Think","created":"2025-05-19","cited_by_count":147},{"id":"2311.08692","title":"Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models","created":"2023-11-15","cited_by_count":145},{"id":"2310.12963","title":"AutoMix: Automatically Mixing Language Models","created":"2023-10-19","cited_by_count":125},{"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},{"id":"2410.10347","title":"A Unified Approach to Routing and Cascading for LLMs","created":"2024-10-14","cited_by_count":80},{"id":"2506.09033","title":"Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning","created":"2025-06-10","cited_by_count":72},{"id":"2402.09997","title":"LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild","created":"2024-02-15","cited_by_count":68},{"id":"2410.13284","title":"Learning to Route LLMs with Confidence Tokens","created":"2024-10-17","cited_by_count":67},{"id":"2506.22716","title":"BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute","created":"2025-06-28","cited_by_count":67},{"id":"2406.13415","title":"Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators","created":"2024-06-19","cited_by_count":61},{"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},{"id":"2502.18482","title":"MixLLM: Dynamic Routing in Mixed Large Language Models","created":"2025-02-09","cited_by_count":59},{"id":"2301.13294","title":"Adaptive Machine Translation with Large Language Models","created":"2023-01-30","cited_by_count":58},{"id":"2407.10834","title":"MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs","created":"2024-07-15","cited_by_count":41},{"id":"2506.01048","title":"IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory","created":"2025-06-01","cited_by_count":40},{"id":"2601.07206","title":"LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing","created":"2026-01-12","cited_by_count":38},{"id":"2409.15518","title":"Eagle: Efficient Training-Free Router for Multi-LLM Inference","created":"2024-09-23","cited_by_count":35},{"id":"2508.13141","title":"OptimalThinkingBench: Evaluating Over and Underthinking in LLMs","created":"2025-08-18","cited_by_count":35},{"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},{"id":"2306.03900","title":"Model Spider: Learning to Rank Pre-Trained Models Efficiently","created":"2023-06-06","cited_by_count":32},{"id":"2502.04428","title":"Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization","created":"2025-02-06","cited_by_count":29},{"id":"2505.21600","title":"R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing","created":"2025-05-27","cited_by_count":29},{"id":"2502.04506","title":"When One LLM Drools, Multi-LLM Collaboration Rules","created":"2025-02-06","cited_by_count":28},{"id":"2505.16037","title":"Causal LLM Routing: End-to-End Regret Minimization from Observational Data","created":"2025-05-21","cited_by_count":28},{"id":"2510.09719","title":"ICL-Router: In-Context Learned Model Representations for LLM Routing","created":"2025-10-10","cited_by_count":28},{"id":"2403.07213","title":"Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits","created":"2024-03-11","cited_by_count":27},{"id":"2505.15400","title":"When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning","created":"2025-05-21","cited_by_count":26},{"id":"2508.21141","title":"Adaptive LLM Routing under Budget Constraints","created":"2025-08-28","cited_by_count":24},{"id":"2510.00202","title":"RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers","created":"2025-09-30","cited_by_count":22},{"id":"2502.11021","title":"Leveraging Uncertainty Estimation for Efficient LLM Routing","created":"2025-02-16","cited_by_count":21},{"id":"2505.18404","title":"Thought calibration: Efficient and confident test-time scaling","created":"2025-05-23","cited_by_count":21},{"id":"2505.19970","title":"CP-Router: An Uncertainty-Aware Router Between LLM and LRM","created":"2025-05-26","cited_by_count":20},{"id":"2310.14451","title":"Domain Terminology Integration into Machine Translation: Leveraging Large Language Models","created":"2023-10-22","cited_by_count":17},{"id":"2510.08439","title":"xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning","created":"2025-10-09","cited_by_count":17},{"id":"2506.05901","title":"Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router","created":"2025-06-06","cited_by_count":13},{"id":"2601.17814","title":"MMR-Bench: A Comprehensive Benchmark for Multimodal LLM Routing","created":"2026-01-25","cited_by_count":13},{"id":"2510.08731","title":"When to Reason: Semantic Router for vLLM","created":"2025-10-09","cited_by_count":12},{"id":"2501.01818","title":"Rerouting LLM Routers","created":"2025-01-03","cited_by_count":11},{"id":"2504.07113","title":"How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities","created":"2025-03-20","cited_by_count":11},{"id":"2602.03478","title":"When Routing Collapses: On the Degenerate Convergence of LLM Routers","created":"2026-02-03","cited_by_count":10},{"id":"2506.16655","title":"Arch-Router: Aligning LLM Routing with Human Preferences","created":"2025-06-19","cited_by_count":9},{"id":"2512.23562","title":"VL-RouterBench: A Benchmark for Vision-Language Model Routing","created":"2025-12-29","cited_by_count":8},{"id":"2510.00841","title":"LLM Routing with Dueling Feedback","created":"2025-10-01","cited_by_count":7},{"id":"2510.05164","title":"SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascading","created":"2025-10-04","cited_by_count":7},{"id":"2602.05176","title":"Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems","created":"2026-02-05","cited_by_count":7},{"id":"2508.10175","title":"Estimating Machine Translation Difficulty","created":"2025-08-13","cited_by_count":6},{"id":"2601.21795","title":"Effective LoRA Adapter Routing using Task Representations","created":"2026-01-29","cited_by_count":6},{"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},{"id":"2511.08590","title":"GMTRouter: Personalized LLM Router over Multi-turn User Interactions","created":"2025-10-29","cited_by_count":5},{"id":"2502.12701","title":"Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferral","created":"2025-02-18","cited_by_count":4},{"id":"2601.22323","title":"Models Under SCOPE: Scalable and Controllable Routing via Pre-hoc Reasoning","created":"2026-01-29","cited_by_count":4},{"id":"2601.05903","title":"HAPS: Hierarchical LLM Routing with Joint Architecture and Parameter Search","created":"2026-01-09","cited_by_count":3},{"id":"2601.17551","title":"GreenServ: Energy-Efficient Context-Aware Dynamic Routing for Multi-Model LLM Inference","created":"2026-01-24","cited_by_count":3},{"id":"2602.02061","title":"Learning to Route and Schedule LLMs from User Retrials via Contextual Queueing Bandits","created":"2026-02-02","cited_by_count":3},{"id":"2602.11877","title":"Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems","created":"2026-02-12","cited_by_count":3},{"id":"2505.13554","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","created":"2025-05-19","cited_by_count":2},{"id":"2602.09902","title":"Routing, Cascades, and User Choice for LLMs","created":"2026-02-10","cited_by_count":2},{"id":"2509.17000","title":"Adaptive Overclocking: Dynamic Control of Thinking Path Length via Real-Time Reasoning Signals","created":"2025-09-21","cited_by_count":1}],"next_cursor":null}