{"total":150,"rows":[{"id":"2504.20073","title":"RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning","created":"2025-04-24","cited_by_count":386,"area":"agents"},{"id":"2501.11651","title":"T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling","created":"2025-01-20","cited_by_count":77,"area":"lr"},{"id":"2503.04482","title":"Generalized Interpolating Discrete Diffusion","created":"2025-03-06","cited_by_count":70,"area":"diffusion"},{"id":"2501.18101","title":"Diverse Preference Optimization","created":"2025-01-30","cited_by_count":52,"area":"lr"},{"id":"2503.17126","title":"Modifying Large Language Model Post-Training for Diverse Creative Writing","created":"2025-03-21","cited_by_count":40,"area":"alignment"},{"id":"2504.10478","title":"Weight Ensembling Improves Reasoning in Language Models","created":"2025-04-14","cited_by_count":38,"area":"lr"},{"id":"2506.02314","title":"ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code","created":"2025-06-02","cited_by_count":36,"area":null},{"id":"2507.14172","title":"Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI","created":"2025-07-10","cited_by_count":36,"area":"synth"},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"id":"2502.05234","title":"Optimizing Temperature for Language Models with Multi-Sample Inference","created":"2025-02-07","cited_by_count":33,"area":"lr"},{"id":"2502.17543","title":"Training a Generally Curious Agent","created":"2025-02-24","cited_by_count":31,"area":"agents"},{"id":"2505.14442","title":"Creative Preference Optimization","created":"2025-05-20","cited_by_count":25,"area":"alignment"},{"id":"2510.03222","title":"Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward","created":"2025-10-03","cited_by_count":25,"area":"lr"},{"id":"2511.08594","title":"Diverse Preference Learning for Capabilities and Alignment","created":"2025-10-29","cited_by_count":25,"area":"alignment"},{"id":"2509.04784","title":"Post-training Large Language Models for Diverse High-Quality Responses","created":"2025-09-05","cited_by_count":19,"area":null},{"id":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2505.17505","title":"L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models","created":"2025-05-23","cited_by_count":15,"area":null},{"id":"2510.01218","title":"Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs","created":"2025-09-20","cited_by_count":15,"area":null},{"id":"2504.08893","title":"Knowledge Graph-extended Retrieval Augmented Generation for Question Answering","created":"2025-04-11","cited_by_count":14,"area":"rag"},{"id":"2511.00432","title":"G2: Guided Generation for Enhanced Output Diversity in LLMs","created":"2025-11-01","cited_by_count":14,"area":null},{"id":"2601.07353","title":"TALON: Confidence-Aware Speculative Decoding with Adaptive Token Trees","created":"2026-01-12","cited_by_count":13,"area":"inference"},{"id":"2410.12323","title":"Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up","created":"2024-10-16","cited_by_count":10,"area":"lr"},{"id":"2505.19371","title":"Foundations of Top-$k$ Decoding For Language Models","created":"2025-05-25","cited_by_count":10,"area":null},{"id":"2506.13681","title":"Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Models","created":"2025-06-16","cited_by_count":10,"area":null},{"id":"2507.02974","title":"InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy","created":"2025-06-30","cited_by_count":10,"area":"rag"},{"id":"2508.20757","title":"GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation","created":"2025-08-28","cited_by_count":10,"area":null},{"id":"2511.12596","title":"Group-Aware Reinforcement Learning for Output Diversity in Large Language Models","created":"2025-11-16","cited_by_count":10,"area":null},{"id":"2411.02989","title":"Growing a Tail: Increasing Output Diversity in Large Language Models","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2506.20544","title":"When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs","created":"2025-06-25","cited_by_count":9,"area":"lr"},{"id":"2509.02510","title":"Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation","created":"2025-09-02","cited_by_count":9,"area":null},{"id":"2509.17570","title":"Asking a Language Model for Diverse Responses","created":"2025-09-22","cited_by_count":9,"area":"lr"},{"id":"2511.04934","title":"Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding","created":"2025-11-07","cited_by_count":9,"area":"safety"},{"id":"2512.15586","title":"Bolmo: Byteifying the Next Generation of Language Models","created":"2025-12-17","cited_by_count":9,"area":null},{"id":"2604.11012","title":"Min-$k$ Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics","created":"2026-04-13","cited_by_count":9,"area":null},{"id":"2503.10573","title":"Evaluating Mathematical Reasoning Across Large Language Models: A Fine-Grained Approach","created":"2025-03-13","cited_by_count":8,"area":"lr"},{"id":"2511.05650","title":"Optimizing Diversity and Quality through Base-Aligned Model Collaboration","created":"2025-11-07","cited_by_count":8,"area":null},{"id":"2602.11683","title":"ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces","created":"2026-02-12","cited_by_count":8,"area":"lr"},{"id":"2604.00499","title":"Scheduling LLM Inference with Uncertainty-Aware Output Length Predictions","created":"2026-04-01","cited_by_count":8,"area":null},{"id":"2505.23816","title":"A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs","created":"2025-05-27","cited_by_count":7,"area":"lr"},{"id":"2506.00457","title":"Revisiting LLMs as Zero-Shot Time-Series Forecasters: Small Noise Can Break Large Models","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2506.19882","title":"Position: Machine Learning Conferences Should Establish a \"Refutations and Critiques\" Track","created":"2025-06-24","cited_by_count":7,"area":null},{"id":"2602.18176","title":"Improving Sampling for Masked Diffusion Models via Information Gain","created":"2026-02-20","cited_by_count":7,"area":"diffusion"},{"id":"2505.02363","title":"SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning","created":"2025-05-05","cited_by_count":6,"area":"alignment"},{"id":"2509.02170","title":"Avoidance Decoding for Diverse Multi-Branch Story Generation","created":"2025-09-02","cited_by_count":6,"area":null},{"id":"2602.18232","title":"Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning","created":"2026-02-20","cited_by_count":6,"area":"lr"},{"id":"2605.11258","title":"Unlocking LLM Creativity in Science through Analogical Reasoning","created":"2026-05-11","cited_by_count":6,"area":"lr"},{"id":"2505.11788","title":"Communication-Efficient Hybrid Language Model via Uncertainty-Aware Opportunistic and Compressed Transmission","created":"2025-05-17","cited_by_count":5,"area":null},{"id":"2509.23234","title":"p-less Sampling: A Robust Hyperparameter-Free Approach for LLM Decoding","created":"2025-09-27","cited_by_count":5,"area":null},{"id":"2510.05987","title":"Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs","created":"2025-10-07","cited_by_count":5,"area":"lr"},{"id":"2510.13940","title":"Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention","created":"2025-10-15","cited_by_count":5,"area":"lr"},{"id":"2602.23116","title":"Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences","created":"2026-02-26","cited_by_count":5,"area":"alignment"},{"id":"2502.11115","title":"Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probability","created":"2025-02-16","cited_by_count":4,"area":null},{"id":"2505.01954","title":"Semantic Probabilistic Control of Language Models","created":"2025-05-04","cited_by_count":4,"area":null},{"id":"2506.17299","title":"Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem","created":"2025-06-17","cited_by_count":4,"area":"safety"},{"id":"2508.06094","title":"ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline","created":"2025-08-08","cited_by_count":4,"area":null},{"id":"2602.01698","title":"Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2602.04208","title":"SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models","created":"2026-02-04","cited_by_count":4,"area":"lr"},{"id":"2605.00195","title":"Diversity in Large Language Models under Supervised Fine-Tuning","created":"2026-04-30","cited_by_count":4,"area":"alignment"},{"id":"2605.05365","title":"ZAYA1-8B Technical Report","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2502.14037","title":"DiffSampling: Enhancing Diversity and Accuracy in Neural Text Generation","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2601.22629","title":"Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2602.10346","title":"Geometry-Aware Decoding with Wasserstein-Regularized Truncation and Mass Penalties for Large Language Models","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2603.09065","title":"Learning Adaptive LLM Decoding","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2603.15854","title":"FlashSampling: Fast and Memory-Efficient Exact Sampling","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2603.18482","title":"The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2502.08436","title":"From Haystack to Needle: Label Space Reduction for Zero-shot Classification","created":"2025-02-12","cited_by_count":2,"area":null},{"id":"2504.03814","title":"Recursive Training Loops in LLMs: How training data properties modulate distribution shift in generated data?","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2506.10157","title":"One Patient, Many Contexts: Scaling Medical AI with Contextual Intelligence","created":"2025-06-11","cited_by_count":2,"area":"mllm"},{"id":"2507.03038","title":"Cautious Next Token Prediction","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2507.21934","title":"Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation","created":"2025-07-29","cited_by_count":2,"area":"rag"},{"id":"2510.03310","title":"Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Management","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.17045","title":"Video Reasoning without Training","created":"2025-10-19","cited_by_count":2,"area":"lr"},{"id":"2512.23087","title":"Dynamic Vocabulary Pruning: Stable LLM-RL by Taming the Tail","created":"2025-12-28","cited_by_count":2,"area":null},{"id":"2602.06418","title":"Adaptive Protein Tokenization","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2602.17691","title":"Tethered Reasoning: Decoupling Entropy from Hallucination in Quantized LLMs via Manifold Steering","created":"2026-02-06","cited_by_count":2,"area":"lr"},{"id":"2603.14355","title":"Exposing Long-Tail Safety Failures in Large Language Models through Efficient Diverse Response Sampling","created":"2026-03-15","cited_by_count":2,"area":"alignment"},{"id":"2603.19519","title":"Inducing Sustained Creativity and Diversity in Large Language Models","created":"2026-03-19","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":"2604.26505","title":"Quantamination: Dynamic Quantization Leaks Your Data Across the Batch","created":"2026-04-29","cited_by_count":2,"area":null},{"id":"2605.11128","title":"Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2605.25773","title":"Efficient Benchmarking Is Just Feature Selection and Multiple Regression","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.10302","title":"Where You Inject Diversity Matters: A Unified Framework for Diverse Generation","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2608.19893","title":"Interrupting the Loop: Periodic Subject Changes Raise Judged Surprise and Connection in Base Language Models","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2411.10951","title":"TSFormer: A Robust Framework for Efficient UHD Image Restoration","created":"2024-11-17","cited_by_count":1,"area":null},{"id":"2502.13207","title":"Thinking Outside the (Gray) Box: A Context-Based Score for Assessing Value and Originality in Neural Text Generation","created":"2025-02-18","cited_by_count":1,"area":"lr"},{"id":"2506.00814","title":"GuessBench: Sensemaking Multimodal Creativity in the Wild","created":"2025-06-01","cited_by_count":1,"area":"mllm"},{"id":"2507.08870","title":"GUIDE: Towards Scalable Advising for Research Ideas","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2509.26169","title":"Alignment-Aware Decoding","created":"2025-09-30","cited_by_count":1,"area":"alignment"},{"id":"2510.12343","title":"Traveling Salesman-Based Token Ordering Improves Stability in Homomorphically Encrypted Language Models","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2510.15061","title":"Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2510.23217","title":"Process Reward Models for Sentence-Level Verification of LVLM Radiology Reports","created":"2025-10-27","cited_by_count":1,"area":"lr"},{"id":"2601.01714","title":"Entropy-Aligned Decoding of LMs for Better Writing and Reasoning","created":"2026-01-05","cited_by_count":1,"area":"lr"},{"id":"2601.22536","title":"Decoding in Geometry: Alleviating Embedding-Space Crowding for Complex Reasoning","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.00238","title":"DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking","created":"2026-01-30","cited_by_count":1,"area":"rag"},{"id":"2602.03195","title":"Reinforcement Learning with Promising Tokens for Large Language Models","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2602.06665","title":"Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2602.22296","title":"UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2603.05352","title":"Ailed: A Psyche-Driven Chess Engine with Dynamic Emotional Modulation","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.07717","title":"Rigidity in LLM Bandits with Implications for Human-AI Dyads","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2604.10971","title":"MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Models","created":"2026-04-13","cited_by_count":1,"area":"mllm"}],"next_cursor":"100"}