{"total":34,"rows":[{"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":"2501.18101","title":"Diverse Preference Optimization","created":"2025-01-30","cited_by_count":52,"area":"lr"},{"id":"2504.10478","title":"Weight Ensembling Improves Reasoning in Language Models","created":"2025-04-14","cited_by_count":38,"area":"lr"},{"id":"2502.05234","title":"Optimizing Temperature for Language Models with Multi-Sample Inference","created":"2025-02-07","cited_by_count":33,"area":"lr"},{"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":"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":"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":"2509.17570","title":"Asking a Language Model for Diverse Responses","created":"2025-09-22","cited_by_count":9,"area":"lr"},{"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":"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":"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":"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":"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":"2602.01698","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":"2605.05365","title":"ZAYA1-8B Technical Report","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"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":"2510.17045","title":"Video Reasoning without Training","created":"2025-10-19","cited_by_count":2,"area":"lr"},{"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":"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":"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":"2602.22296","title":"UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2604.20500","title":"Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2605.30789","title":"Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2503.01819","title":"Do GFlowNets Transfer? Case Study on the Game of 24/42","created":"2025-03-03","cited_by_count":0,"area":"lr"},{"id":"2509.08358","title":"<think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs","created":"2025-09-10","cited_by_count":0,"area":"lr"},{"id":"2604.24927","title":"Large Language Models Explore by Latent Distilling","created":"2026-04-27","cited_by_count":0,"area":"lr"},{"id":"2606.10768","title":"N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2607.11317","title":"Calibrated e-CUSUM Decoding for Quantized Reasoning Models: Why Token Log-Probability Is the Wrong Observable for Decoding Monitors","created":"2026-07-13","cited_by_count":0,"area":"lr"},{"id":"2609.38104","title":"Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}