{"total":48,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2507.06203","title":"A Survey on Latent Reasoning","created":"2025-07-08","cited_by_count":81,"area":"lr"},{"id":"2507.08838","title":"wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models","created":"2025-07-07","cited_by_count":71,"area":"lr"},{"id":"2508.02558","title":"Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction","created":"2025-08-04","cited_by_count":65,"area":"lr"},{"id":"2510.08554","title":"Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization","created":"2025-10-09","cited_by_count":33,"area":"lr"},{"id":"2509.21474","title":"d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation","created":"2025-09-25","cited_by_count":27,"area":"lr"},{"id":"2507.19227","title":"Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation","created":"2025-07-25","cited_by_count":26,"area":"lr"},{"id":"2510.08233","title":"Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization","created":"2025-10-09","cited_by_count":20,"area":"lr"},{"id":"2510.02212","title":"DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning","created":"2025-10-02","cited_by_count":19,"area":"lr"},{"id":"2601.15165","title":"The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models","created":"2026-01-21","cited_by_count":18,"area":"lr"},{"id":"2512.09675","title":"d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models","created":"2025-12-10","cited_by_count":17,"area":"lr"},{"id":"2512.04459","title":"dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoning","created":"2025-12-04","cited_by_count":14,"area":"lr"},{"id":"2510.02880","title":"Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models","created":"2025-10-03","cited_by_count":12,"area":"lr"},{"id":"2510.04019","title":"Simple Policy Gradients for Reasoning with Diffusion Language Models","created":"2025-10-05","cited_by_count":12,"area":"lr"},{"id":"2603.06743","title":"Stabilizing Reinforcement Learning for Diffusion Language Models","created":"2026-03-06","cited_by_count":10,"area":"lr"},{"id":"2509.25604","title":"RFG: Test-Time Scaling for Diffusion Large Language Model Reasoning with Reward-Free Guidance","created":"2025-09-29","cited_by_count":7,"area":"lr"},{"id":"2602.01705","title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2512.22288","title":"Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Model","created":"2025-12-25","cited_by_count":6,"area":"lr"},{"id":"2606.29150","title":"Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners","created":"2026-06-28","cited_by_count":6,"area":"lr"},{"id":"2601.21484","title":"ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment","created":"2026-01-29","cited_by_count":5,"area":"lr"},{"id":"2606.19257","title":"DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models","created":"2026-06-17","cited_by_count":5,"area":"lr"},{"id":"2510.09544","title":"Beyond Surface Reasoning: Unveiling the True Long Chain-of-Thought Capacity of Diffusion Large Language Models","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2602.01849","title":"Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2603.27593","title":"STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding","created":"2026-03-29","cited_by_count":4,"area":"lr"},{"id":"2606.08501","title":"Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models","created":"2026-06-07","cited_by_count":4,"area":"lr"},{"id":"2511.15208","title":"Reasoning in Diffusion Large Language Models is Concentrated in Dynamic Confusion Zones","created":"2025-11-19","cited_by_count":3,"area":"lr"},{"id":"2603.01331","title":"MetaState: Persistent Working Memory Enhances Reasoning in Discrete Diffusion Language Models","created":"2026-03-02","cited_by_count":3,"area":"lr"},{"id":"2603.01563","title":"LFPO: Likelihood-Free Policy Optimization for Masked Diffusion Models","created":"2026-03-02","cited_by_count":3,"area":"lr"},{"id":"2604.02621","title":"Reinforcement Learning-based Semi-supervised Knowledge Distillation with LLM-as-a-Judge","created":"2026-04-03","cited_by_count":3,"area":"lr"},{"id":"2605.22939","title":"Learnability-Informed Fine-Tuning of Diffusion Language Models","created":"2026-05-21","cited_by_count":3,"area":"lr"},{"id":"2608.05687","title":"Answer First, Reason Later: When Commitment Order Costs Accuracy in Diffusion Language Models","created":"2026-08-06","cited_by_count":3,"area":"lr"},{"id":"2512.19433","title":"dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models","created":"2025-12-22","cited_by_count":2,"area":"lr"},{"id":"2602.04344","title":"UnMaskFork: Test-Time Scaling for Masked Diffusion via Deterministic Action Branching","created":"2026-02-04","cited_by_count":2,"area":"lr"},{"id":"2602.08905","title":"Efficient and Stable Reinforcement Learning for Diffusion Language Models","created":"2026-02-09","cited_by_count":2,"area":"lr"},{"id":"2602.09555","title":"Adaptive Test-Time Compute Allocation for Block Diffusion Language Models in Complex Reasoning","created":"2026-02-10","cited_by_count":2,"area":"lr"},{"id":"2607.24306","title":"Rethinking the Generation Order of Block Diffusion Language Models","created":"2026-07-27","cited_by_count":2,"area":"lr"},{"id":"2605.02263","title":"Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning","created":"2026-05-04","cited_by_count":1,"area":"lr"},{"id":"2605.10218","title":"Relative Score Policy Optimization for Diffusion Language Models","created":"2026-05-11","cited_by_count":1,"area":"lr"},{"id":"2601.17426","title":"A Syllogistic Probe: Tracing the Evolution of Logic Reasoning in Large Language Models","created":"2026-01-24","cited_by_count":0,"area":"lr"},{"id":"2602.13310","title":"Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension","created":"2026-02-10","cited_by_count":0,"area":"lr"},{"id":"2603.23964","title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2605.11726","title":"Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2607.01170","title":"Diffusion-GR2: Diffusion Generative Reasoning Re-ranker","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2608.00605","title":"Escaping Confidence Trap: Evolutionary Decoding for Mathematical Reasoning in Diffusion LLMs","created":"2026-08-01","cited_by_count":0,"area":"lr"},{"id":"2609.16372","title":"Register Tokens for Bounded-State Reasoning in Diffusion Language Models","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.28272","title":"Towards Efficient Reasoning: Learning Causal Shortcuts for Diffusion Language Models","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2609.37391","title":"Rethinking Soft Tokens for Parallel Decoding in Diffusion Language Models","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.15097","title":"Anchors Enhance Controllability and Reasoning of Diffusion Language Models","created":"2026-10-10","cited_by_count":0,"area":"lr"}],"next_cursor":null}