{"total":144,"rows":[{"id":"2604.13016","title":"Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe","created":"2026-04-14","cited_by_count":299,"area":"lr"},{"id":"2508.15260","title":"Deep Think with Confidence","created":"2025-08-21","cited_by_count":205,"area":"lr"},{"id":"2602.12125","title":"Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation","created":"2026-02-12","cited_by_count":184,"area":"lr"},{"id":"2506.09038","title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions","created":"2025-06-10","cited_by_count":145,"area":"lr"},{"id":"2506.13284","title":"AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy","created":"2025-06-16","cited_by_count":77,"area":"lr"},{"id":"2509.22819","title":"Hilbert: Recursively Building Formal Proofs with Informal Reasoning","created":"2025-09-26","cited_by_count":60,"area":"lr"},{"id":"2508.20722","title":"rStar2-Agent: Agentic Reasoning Technical Report","created":"2025-08-28","cited_by_count":54,"area":"lr"},{"id":"2509.06870","title":"The Majority is not always right: RL training for solution aggregation","created":"2025-09-08","cited_by_count":47,"area":"lr"},{"id":"2507.13266","title":"QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation","created":"2025-07-17","cited_by_count":44,"area":"lr"},{"id":"2510.26768","title":"AMO-Bench: Large Language Models Still Struggle in High School Math Competitions","created":"2025-10-30","cited_by_count":38,"area":"lr"},{"id":"2508.13141","title":"OptimalThinkingBench: Evaluating Over and Underthinking in LLMs","created":"2025-08-18","cited_by_count":35,"area":"lr"},{"id":"2507.05255","title":"Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning","created":"2025-07-07","cited_by_count":34,"area":"lr"},{"id":"2604.13010","title":"Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation","created":"2026-04-14","cited_by_count":33,"area":"lr"},{"id":"2509.13232","title":"Single-stream Policy Optimization","created":"2025-09-16","cited_by_count":28,"area":"lr"},{"id":"2507.15375","title":"STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models","created":"2025-07-21","cited_by_count":26,"area":"lr"},{"id":"2510.04996","title":"Reinforce-Ada: An Adaptive Sampling Framework under Non-linear RL Objectives","created":"2025-10-06","cited_by_count":25,"area":"lr"},{"id":"2602.13517","title":"Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens","created":"2026-02-13","cited_by_count":22,"area":"lr"},{"id":"2509.26574","title":"Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark","created":"2025-09-30","cited_by_count":21,"area":"lr"},{"id":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2510.06672","title":"XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation","created":"2025-10-08","cited_by_count":18,"area":"lr"},{"id":"2510.13888","title":"Reliable Fine-Grained Evaluation of Natural Language Math Proofs","created":"2025-10-14","cited_by_count":18,"area":"lr"},{"id":"2604.09852","title":"MEMENTO: Teaching LLMs to Manage Their Own Context","created":"2026-04-10","cited_by_count":18,"area":"lr"},{"id":"2506.22058","title":"Lost at the Beginning of Reasoning","created":"2025-06-27","cited_by_count":15,"area":"lr"},{"id":"2602.09924","title":"LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations","created":"2026-02-10","cited_by_count":14,"area":"lr"},{"id":"2512.07461","title":"Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning","created":"2025-12-08","cited_by_count":12,"area":"lr"},{"id":"2603.04304","title":"$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners","created":"2026-03-04","cited_by_count":12,"area":"lr"},{"id":"2509.07604","title":"K2-Think: A Parameter-Efficient Reasoning System","created":"2025-09-09","cited_by_count":11,"area":"lr"},{"id":"2601.18984","title":"Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning","created":"2026-01-26","cited_by_count":11,"area":"lr"},{"id":"2602.01058","title":"Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"id":"2603.26535","title":"PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization","created":"2026-03-27","cited_by_count":11,"area":"lr"},{"id":"2508.21787","title":"PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains","created":"2025-08-29","cited_by_count":10,"area":"lr"},{"id":"2509.24981","title":"Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2510.11653","title":"MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model","created":"2025-10-13","cited_by_count":10,"area":"lr"},{"id":"2512.00499","title":"ESPO: Entropy Importance Sampling Policy Optimization","created":"2025-11-29","cited_by_count":9,"area":"lr"},{"id":"2512.07795","title":"ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning","created":"2025-12-08","cited_by_count":9,"area":"lr"},{"id":"2602.16793","title":"Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models","created":"2026-02-18","cited_by_count":9,"area":"lr"},{"id":"2602.22538","title":"RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format","created":"2026-02-26","cited_by_count":9,"area":"lr"},{"id":"2508.08833","title":"An Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical Problems","created":"2025-08-12","cited_by_count":8,"area":"lr"},{"id":"2509.24210","title":"BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models","created":"2025-09-29","cited_by_count":8,"area":"lr"},{"id":"2511.13612","title":"P1: Mastering Physics Olympiads with Reinforcement Learning","created":"2025-11-17","cited_by_count":8,"area":"lr"},{"id":"2605.14392","title":"Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis","created":"2026-05-14","cited_by_count":8,"area":"lr"},{"id":"2510.04182","title":"Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization","created":"2025-10-05","cited_by_count":7,"area":"lr"},{"id":"2605.09725","title":"On-Policy Distillation with Best-of-N Teacher Rollout Selection","created":"2026-05-10","cited_by_count":7,"area":"lr"},{"id":"2607.19313","title":"Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information","created":"2026-07-21","cited_by_count":7,"area":"lr"},{"id":"2512.02874","title":"Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning","created":"2025-12-02","cited_by_count":6,"area":"lr"},{"id":"2602.13367","title":"Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts","created":"2026-02-13","cited_by_count":6,"area":"lr"},{"id":"2604.18584","title":"MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval","created":"2026-04-20","cited_by_count":6,"area":"lr"},{"id":"2606.15079","title":"Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale","created":"2026-06-13","cited_by_count":6,"area":"lr"},{"id":"2601.03703","title":"TreeAdv: Tree-Structured Advantage Redistribution for Group-Based RL","created":"2026-01-07","cited_by_count":5,"area":"lr"},{"id":"2607.28449","title":"Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models","created":"2026-07-30","cited_by_count":5,"area":"lr"},{"id":"2601.01400","title":"EternalMath: A Living Benchmark of Frontier Mathematics that Evolves with Human Discovery","created":"2026-01-04","cited_by_count":4,"area":"lr"},{"id":"2602.02477","title":"Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2602.04288","title":"Contextual Drag: How Errors in the Context Affect LLM Reasoning","created":"2026-02-04","cited_by_count":4,"area":"lr"},{"id":"2603.16157","title":"DyJR: Preserving Diversity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay","created":"2026-03-17","cited_by_count":4,"area":"lr"},{"id":"2605.09063","title":"Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs","created":"2026-05-09","cited_by_count":4,"area":"lr"},{"id":"2605.15726","title":"Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR","created":"2026-05-15","cited_by_count":4,"area":"lr"},{"id":"2509.23633","title":"Fast Thinking for Large Language Models","created":"2025-09-28","cited_by_count":3,"area":"lr"},{"id":"2510.02919","title":"Self-Reflective Generation at Test Time","created":"2025-10-03","cited_by_count":3,"area":"lr"},{"id":"2510.16449","title":"TrajSelector: Harnessing Latent Representations for Efficient and Effective Best-of-N in Large Reasoning Model","created":"2025-10-18","cited_by_count":3,"area":"lr"},{"id":"2512.15274","title":"Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning","created":"2025-12-17","cited_by_count":3,"area":"lr"},{"id":"2601.09980","title":"Performance of AI agents based on reasoning language models on ALD process optimization tasks","created":"2026-01-15","cited_by_count":3,"area":"lr"},{"id":"2603.02479","title":"PRISM: Pushing the Frontier of Deep Think via Process Reward Model-Guided Inference","created":"2026-03-03","cited_by_count":3,"area":"lr"},{"id":"2603.18886","title":"Reasoning over mathematical objects: on-policy reward modeling and test time aggregation","created":"2026-03-19","cited_by_count":3,"area":"lr"},{"id":"2604.02450","title":"Do We Need Frontier Models to Verify Mathematical Proofs?","created":"2026-04-02","cited_by_count":3,"area":"lr"},{"id":"2605.07654","title":"Reliable Chain-of-Thought via Prefix Consistency","created":"2026-05-08","cited_by_count":3,"area":"lr"},{"id":"2605.17333","title":"Leveraging Error Diversity in Group Rollouts for Reinforcement Learning","created":"2026-05-17","cited_by_count":3,"area":"lr"},{"id":"2509.21124","title":"Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought Patterns","created":"2025-09-25","cited_by_count":2,"area":"lr"},{"id":"2602.04248","title":"Empirical-MCTS: Continuous Agent Evolution via Dual-Experience Monte Carlo Tree Search","created":"2026-02-04","cited_by_count":2,"area":"lr"},{"id":"2602.05281","title":"Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2602.11361","title":"Finding the Cracks: Improving LLMs Reasoning with Paraphrastic Probing and Consistency Verification","created":"2026-02-11","cited_by_count":2,"area":"lr"},{"id":"2602.14917","title":"BFS-PO: Best-First Search for Large Reasoning Models","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2603.01335","title":"Provable and Practical In-Context Policy Optimization for Self-Improvement","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2603.03872","title":"Believe Your Model: Distribution-Guided Confidence Calibration","created":"2026-03-04","cited_by_count":2,"area":"lr"},{"id":"2603.16206","title":"Offline Exploration-Aware Fine-Tuning for Long-Chain Mathematical Reasoning","created":"2026-03-17","cited_by_count":2,"area":"lr"},{"id":"2603.27977","title":"SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology","created":"2026-03-30","cited_by_count":2,"area":"lr"},{"id":"2604.22266","title":"Large Language Models Decide Early and Explain Later","created":"2026-04-24","cited_by_count":2,"area":"lr"},{"id":"2605.14619","title":"SliceGraph: Mapping Process Isomers in Multi-Run Chain-of-Thought Reasoning","created":"2026-05-14","cited_by_count":2,"area":"lr"},{"id":"2605.15513","title":"CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning","created":"2026-05-15","cited_by_count":2,"area":"lr"},{"id":"2605.25244","title":"Inference Time Optimization with Confidence Dynamics","created":"2026-05-24","cited_by_count":2,"area":"lr"},{"id":"2606.26472","title":"Epiphany-Aware KV Cache Eviction Without the Attention Matrix","created":"2026-06-25","cited_by_count":2,"area":"lr"},{"id":"2608.02087","title":"Instruction-Conditioned Exploration for Reinforcement Learning with Self-Distillation to an Unconditioned Policy","created":"2026-08-03","cited_by_count":2,"area":"lr"},{"id":"2608.02442","title":"Right Answer, Wrong Method: Shortcut Hacking Misleads the Evaluation of LLM Reasoning on Frontier Science Benchmarks","created":"2026-08-03","cited_by_count":2,"area":"lr"},{"id":"2509.17177","title":"FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions","created":"2025-09-21","cited_by_count":1,"area":"lr"},{"id":"2510.06014","title":"ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models","created":"2025-10-07","cited_by_count":1,"area":"lr"},{"id":"2512.00729","title":"Probing the \"Psyche'' of Large Reasoning Models: Understanding Through a Human Lens","created":"2025-11-30","cited_by_count":1,"area":"lr"},{"id":"2601.23027","title":"Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.22583","title":"Strategy Executability in Mathematical Reasoning: Leveraging Human-Model Differences for Effective Guidance","created":"2026-02-26","cited_by_count":1,"area":"lr"},{"id":"2605.06650","title":"Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2605.07316","title":"Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.09879","title":"M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Models","created":"2026-05-11","cited_by_count":1,"area":"lr"},{"id":"2605.12969","title":"Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2605.21467","title":"DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards","created":"2026-05-20","cited_by_count":1,"area":"lr"},{"id":"2605.27293","title":"BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning","created":"2026-05-26","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":"2606.08850","title":"Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability","created":"2026-06-07","cited_by_count":1,"area":"lr"},{"id":"2606.31484","title":"Fork-Think with Confidence","created":"2026-06-30","cited_by_count":1,"area":"lr"},{"id":"2607.21453","title":"Test-Time Scaling via Error Localization","created":"2026-07-23","cited_by_count":1,"area":"lr"},{"id":"2609.03430","title":"Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning","created":"2026-09-03","cited_by_count":1,"area":"lr"},{"id":"2508.10173","title":"Benchmark-Driven Selection of AI: Evidence from DeepSeek-R1","created":"2025-08-13","cited_by_count":0,"area":"lr"},{"id":"2510.05176","title":"PatternKV: Flattening KV Representation Expands Quantization Headroom","created":"2025-10-05","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}