{"total":47,"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":"2505.10446","title":"Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models","created":"2025-05-15","cited_by_count":54,"area":"lr"},{"id":"2509.04475","title":"ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute","created":"2025-08-30","cited_by_count":38,"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":"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":"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":"2505.22524","title":"Inference-Time Scaling of Discrete Diffusion Models via Importance Weighting and Optimal Proposal Design","created":"2025-05-28","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":"2602.23225","title":"Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?","created":"2026-02-26","cited_by_count":11,"area":"lr"},{"id":"2505.22756","title":"Decomposing Elements of Problem Solving: What \"Math\" Does RL Teach?","created":"2025-05-28","cited_by_count":10,"area":"lr"},{"id":"2510.01544","title":"Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards","created":"2025-10-02","cited_by_count":10,"area":"lr"},{"id":"2603.06743","title":"Stabilizing Reinforcement Learning for Diffusion Language Models","created":"2026-03-06","cited_by_count":10,"area":"lr"},{"id":"2507.08390","title":"Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement","created":"2025-07-11","cited_by_count":7,"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":"2602.14147","title":"LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models","created":"2026-02-15","cited_by_count":7,"area":"lr"},{"id":"2510.05132","title":"Training Large Language Models To Reason In Parallel With Global Forking Tokens","created":"2025-10-01","cited_by_count":6,"area":"lr"},{"id":"2603.13319","title":"LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning","created":"2026-03-04","cited_by_count":6,"area":"lr"},{"id":"2604.00375","title":"Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Models","created":"2026-04-01","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":"2510.19990","title":"Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and Beyond","created":"2025-10-22","cited_by_count":4,"area":"lr"},{"id":"2606.06447","title":"Latent Reasoning with Normalizing Flows","created":"2026-06-04","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":"2510.15244","title":"Planner and Executor: Collaboration between Discrete Diffusion And Autoregressive Models in Reasoning","created":"2025-10-17","cited_by_count":3,"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":"2603.01563","title":"LFPO: Likelihood-Free Policy Optimization for Masked Diffusion Models","created":"2026-03-02","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":"2607.15200","title":"Mask-Aware Policy Gradients for Diffusion Language Models","created":"2026-07-16","cited_by_count":3,"area":"lr"},{"id":"2510.09599","title":"Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation","created":"2025-10-10","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":"2604.06260","title":"$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models","created":"2026-04-07","cited_by_count":2,"area":"lr"},{"id":"2604.16565","title":"Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models","created":"2026-04-17","cited_by_count":2,"area":"lr"},{"id":"2603.13243","title":"Think First, Diffuse Fast: Improving Diffusion Language Model Reasoning via Autoregressive Plan Conditioning","created":"2026-02-20","cited_by_count":1,"area":"lr"},{"id":"2603.26771","title":"LogicDiff: Logic-Guided Denoising Improves Zero-Shot Reasoning in Masked Diffusion Language Models","created":"2026-03-24","cited_by_count":1,"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":"2605.29123","title":"The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.23567","title":"Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models","created":"2026-06-22","cited_by_count":1,"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":"2609.13060","title":"CanvasAnneal: Curriculum Reinforcement Learning for Diffusion Language Models","created":"2026-09-11","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":"2610.00661","title":"Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}