{"total":22,"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":"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":"2510.04573","title":"LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning","created":"2025-10-06","cited_by_count":29,"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":"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":"2603.22458","title":"MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding","created":"2026-03-23","cited_by_count":8,"area":"lr"},{"id":"2510.13117","title":"On the Reasoning Abilities of Masked Diffusion Language Models","created":"2025-10-15","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":"2602.01842","title":"Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2510.04704","title":"AtomWorld: A Benchmark for Evaluating Spatial Reasoning in Large Language Models on Crystalline Materials","created":"2025-10-06","cited_by_count":5,"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":"2511.19473","title":"WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoning","created":"2025-11-22","cited_by_count":4,"area":"lr"},{"id":"2512.20573","title":"Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs","created":"2025-12-23","cited_by_count":4,"area":"lr"},{"id":"2601.10348","title":"Training-Trajectory-Aware Token Selection","created":"2026-01-15","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":"2605.14465","title":"From Table to Cell: Attention for Better Reasoning with TABALIGN","created":"2026-05-14","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":"2509.20744","title":"Parallel Thinking, Sequential Answering: Bridging NAR and AR for Efficient Reasoning","created":"2025-09-25","cited_by_count":0,"area":"lr"},{"id":"2606.16700","title":"Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models","created":"2026-06-15","cited_by_count":0,"area":"lr"}],"next_cursor":null}