{"total":122,"rows":[{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2504.12216","title":"d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning","created":"2025-04-16","cited_by_count":186,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2505.16839","title":"LaViDa: A Large Diffusion Language Model for Multimodal Understanding","created":"2025-05-22","cited_by_count":84,"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":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61,"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":"2504.01005","title":"When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning","created":"2025-04-01","cited_by_count":42,"area":"lr"},{"id":"2509.22647","title":"CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning","created":"2025-09-26","cited_by_count":38,"area":"lr"},{"id":"2511.08923","title":"TiDAR: Think in Diffusion, Talk in Autoregression","created":"2025-11-12","cited_by_count":37,"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":"2510.03206","title":"Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner","created":"2025-10-03","cited_by_count":32,"area":"lr"},{"id":"2507.02076","title":"Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs","created":"2025-07-02","cited_by_count":31,"area":"lr"},{"id":"2509.25681","title":"dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought","created":"2025-09-30","cited_by_count":30,"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":"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":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2605.11011","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","created":"2026-05-10","cited_by_count":15,"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":"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":"2505.13138","title":"Neurosymbolic Diffusion Models","created":"2025-05-19","cited_by_count":13,"area":"lr"},{"id":"2508.10736","title":"Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs","created":"2025-08-14","cited_by_count":13,"area":"lr"},{"id":"2503.07154","title":"Ideas in Inference-time Scaling can Benefit Generative Pre-training Algorithms","created":"2025-03-10","cited_by_count":12,"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":"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":"2512.15176","title":"DEER: Draft with Diffusion, Verify with Autoregressive Models","created":"2025-12-17","cited_by_count":9,"area":"lr"},{"id":"2602.03769","title":"Reasoning with Latent Tokens in Diffusion Language Models","created":"2026-02-03","cited_by_count":9,"area":"lr"},{"id":"2510.05040","title":"Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts","created":"2025-10-06","cited_by_count":8,"area":"lr"},{"id":"2510.11462","title":"Unifying Deductive and Abductive Reasoning in Knowledge Graphs with Masked Diffusion Model","created":"2025-10-13","cited_by_count":8,"area":"lr"},{"id":"2511.05562","title":"Effective Test-Time Scaling of Discrete Diffusion through Iterative Refinement","created":"2025-11-04","cited_by_count":8,"area":"lr"},{"id":"2603.09786","title":"Quantifying the Necessity of Chain of Thought through Opaque Serial Depth","created":"2026-03-10","cited_by_count":8,"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":"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":"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":"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":"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":"2507.00004","title":"A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search","created":"2025-06-10","cited_by_count":5,"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":"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":"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":"2606.19257","title":"DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models","created":"2026-06-17","cited_by_count":5,"area":"lr"},{"id":"2508.05305","title":"SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens","created":"2025-08-07","cited_by_count":4,"area":"lr"},{"id":"2508.13070","title":"Reinforced Context Order Recovery for Adaptive Reasoning and Planning","created":"2025-08-18","cited_by_count":4,"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":"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":"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":"2606.06447","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":"2606.12594","title":"Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation","created":"2026-06-10","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":"2601.22629","title":"Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models","created":"2026-01-30","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":"2604.05497","title":"Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models","created":"2026-04-07","cited_by_count":3,"area":"lr"},{"id":"2605.13382","title":"BlockVLA: Accelerating Autoregressive VLA via Block Diffusion Finetuning","created":"2026-05-13","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":"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":"2602.02470","title":"Breaking the Reversal Curse in Autoregressive Language Models via Identity Bridge","created":"2026-02-02","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":"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":"2605.14465","title":"From Table to Cell: Attention for Better Reasoning with TABALIGN","created":"2026-05-14","cited_by_count":2,"area":"lr"},{"id":"2605.17850","title":"Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures","created":"2026-05-18","cited_by_count":2,"area":"lr"},{"id":"2606.00642","title":"Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs","created":"2026-05-30","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":"2508.10995","title":"Improving Text Style Transfer using Masked Diffusion Language Models with Inference-time Scaling","created":"2025-08-14","cited_by_count":1,"area":"lr"},{"id":"2601.22035","title":"Thinking Out of Order: When Output Order Stops Reflecting Reasoning Order in Diffusion Language Models","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2603.09184","title":"Latent-DARM: Bridging Discrete Diffusion And Autoregressive Models For Reasoning","created":"2026-03-10","cited_by_count":1,"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":"2604.03537","title":"Rethinking Token Prediction: Tree-Structured Diffusion Language Model","created":"2026-04-04","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":"2605.22967","title":"Learned Relay Representations for Forward-Thinking Discrete Diffusion Models","created":"2026-05-21","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":"2607.17884","title":"ST-Veto: Spatio-Temporal Token Veto for Diffusion MLLMs via Taylor Prediction and Visual Grounding","created":"2026-07-20","cited_by_count":1,"area":"lr"},{"id":"2609.29102","title":"ELF-REG: Scaling Continuous Diffusion Language Models to Reasoning Tasks","created":"2026-09-24","cited_by_count":1,"area":"lr"},{"id":"2609.32448","title":"ForkLeft: Entropy-First Rollouts for Prefix-Aligned Autoregressive-to-Diffusion Distillation","created":"2026-09-26","cited_by_count":1,"area":"lr"},{"id":"2509.05249","title":"COGITAO: A Visual Reasoning Framework To Study Compositionality & Generalization","created":"2025-09-05","cited_by_count":0,"area":"lr"},{"id":"2512.21257","title":"ReaSeq: Unleashing World Knowledge via Reasoning for Sequential Modeling","created":"2025-12-24","cited_by_count":0,"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"}],"next_cursor":"100"}