{"total":200,"rows":[{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"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":"2602.12125","title":"Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation","created":"2026-02-12","cited_by_count":184,"area":"lr"},{"id":"2510.25741","title":"Scaling Latent Reasoning via Looped Language Models","created":"2025-10-29","cited_by_count":165,"area":"lr"},{"id":"2507.00432","title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","created":"2025-07-01","cited_by_count":106,"area":"lr"},{"id":"2508.11408","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","created":"2025-08-15","cited_by_count":91,"area":"lr"},{"id":"2507.16812","title":"MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning","created":"2025-07-22","cited_by_count":59,"area":"lr"},{"id":"2508.07629","title":"Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization","created":"2025-08-11","cited_by_count":39,"area":"lr"},{"id":"2509.21268","title":"MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources","created":"2025-09-25","cited_by_count":39,"area":"lr"},{"id":"2511.16334","title":"OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe","created":"2025-11-20","cited_by_count":37,"area":"lr"},{"id":"2605.06387","title":"Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level","created":"2026-05-07","cited_by_count":35,"area":"lr"},{"id":"2509.21128","title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs","created":"2025-09-25","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":"2507.01921","title":"NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning Tasks","created":"2025-07-02","cited_by_count":32,"area":"lr"},{"id":"2601.21821","title":"MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods","created":"2026-01-29","cited_by_count":30,"area":"lr"},{"id":"2510.01624","title":"Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead","created":"2025-10-02","cited_by_count":28,"area":"lr"},{"id":"2508.02669","title":"MedVLThinker: Simple Baselines for Multimodal Medical Reasoning","created":"2025-08-04","cited_by_count":27,"area":"lr"},{"id":"2510.03264","title":"Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data","created":"2025-09-26","cited_by_count":27,"area":"lr"},{"id":"2511.16660","title":"Cognitive Foundations for Reasoning and Their Manifestation in LLMs","created":"2025-11-20","cited_by_count":26,"area":"lr"},{"id":"2512.12895","title":"Wait, Wait, Wait... Why Do Reasoning Models Loop?","created":"2025-12-15","cited_by_count":26,"area":"lr"},{"id":"2603.05706","title":"Reasoning Models Struggle to Control their Chains of Thought","created":"2026-03-05","cited_by_count":25,"area":"lr"},{"id":"2605.13255","title":"Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning","created":"2026-05-13","cited_by_count":23,"area":"lr"},{"id":"2506.19807","title":"KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality","created":"2025-06-24","cited_by_count":20,"area":"lr"},{"id":"2510.01833","title":"Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning","created":"2025-10-02","cited_by_count":19,"area":"lr"},{"id":"2510.10409","title":"Trace Length is a Simple Uncertainty Signal in Reasoning Models","created":"2025-10-12","cited_by_count":19,"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":"2507.12428","title":"Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models","created":"2025-07-16","cited_by_count":17,"area":"lr"},{"id":"2510.08457","title":"ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping","created":"2025-10-09","cited_by_count":17,"area":"lr"},{"id":"2512.20745","title":"AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent","created":"2025-12-23","cited_by_count":17,"area":"lr"},{"id":"2601.05593","title":"PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning","created":"2026-01-09","cited_by_count":17,"area":"lr"},{"id":"2601.09088","title":"Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning","created":"2026-01-14","cited_by_count":17,"area":"lr"},{"id":"2608.06296","title":"On-Policy Self-Distillation without Any Supervision","created":"2026-08-06","cited_by_count":17,"area":"lr"},{"id":"2508.17784","title":"Proximal Supervised Fine-Tuning","created":"2025-08-25","cited_by_count":16,"area":"lr"},{"id":"2601.14209","title":"InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning","created":"2026-01-20","cited_by_count":14,"area":"lr"},{"id":"2602.04118","title":"Learning to Reason in 13 Parameters","created":"2026-02-04","cited_by_count":14,"area":"lr"},{"id":"2605.11458","title":"Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning","created":"2026-05-12","cited_by_count":14,"area":"lr"},{"id":"2510.12225","title":"HoneyBee: Data Recipes for Vision-Language Reasoners","created":"2025-10-14","cited_by_count":13,"area":"lr"},{"id":"2601.02346","title":"Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling","created":"2026-01-05","cited_by_count":13,"area":"lr"},{"id":"2601.14249","title":"Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment","created":"2026-01-20","cited_by_count":13,"area":"lr"},{"id":"2603.12246","title":"Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training","created":"2026-03-12","cited_by_count":13,"area":"lr"},{"id":"2606.00305","title":"Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance","created":"2026-05-29","cited_by_count":13,"area":"lr"},{"id":"2507.14683","title":"MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization","created":"2025-07-19","cited_by_count":12,"area":"lr"},{"id":"2510.20956","title":"Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training","created":"2025-10-23","cited_by_count":12,"area":"lr"},{"id":"2601.05679","title":"Do Sparse Autoencoders Identify Reasoning Features in Language Models?","created":"2026-01-09","cited_by_count":12,"area":"lr"},{"id":"2602.03279","title":"Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis","created":"2026-02-03","cited_by_count":12,"area":"lr"},{"id":"2605.05040","title":"Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization","created":"2026-05-06","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":"2512.22255","title":"Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks","created":"2025-12-24","cited_by_count":11,"area":"lr"},{"id":"2510.04230","title":"Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought","created":"2025-10-05","cited_by_count":10,"area":"lr"},{"id":"2511.23269","title":"OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning","created":"2025-11-28","cited_by_count":10,"area":"lr"},{"id":"2601.18091","title":"From LLMs to LRMs: Rethinking Pruning for Reasoning-Centric Models","created":"2026-01-26","cited_by_count":10,"area":"lr"},{"id":"2605.09548","title":"Crosslingual On-Policy Self-Distillation for Multilingual Reasoning","created":"2026-05-10","cited_by_count":10,"area":"lr"},{"id":"2605.17497","title":"Self-Supervised On-Policy Distillation for Reasoning Language Models","created":"2026-05-17","cited_by_count":10,"area":"lr"},{"id":"2606.00564","title":"Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding","created":"2026-05-30","cited_by_count":10,"area":"lr"},{"id":"2509.19894","title":"PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning","created":"2025-09-24","cited_by_count":9,"area":"lr"},{"id":"2510.02386","title":"On The Fragility of Benchmark Contamination Detection in Reasoning Models","created":"2025-09-30","cited_by_count":9,"area":"lr"},{"id":"2602.02301","title":"Advancing General-Purpose Reasoning Models with Modular Gradient Surgery","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2608.09867","title":"Stealing Reasoning Traces from Proprietary LLM APIs","created":"2026-08-10","cited_by_count":9,"area":"lr"},{"id":"2507.12885","title":"VAR-MATH: Probing True Mathematical Reasoning in LLMS via Symbolic Multi-Instance Benchmarks","created":"2025-07-17","cited_by_count":8,"area":"lr"},{"id":"2509.22637","title":"Variational Reasoning for Language Models","created":"2025-09-26","cited_by_count":8,"area":"lr"},{"id":"2510.08189","title":"R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?","created":"2025-10-09","cited_by_count":8,"area":"lr"},{"id":"2511.22586","title":"Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalization","created":"2025-11-27","cited_by_count":8,"area":"lr"},{"id":"2512.01127","title":"Mode-Conditioning Unlocks Superior Test-Time Scaling","created":"2025-11-30","cited_by_count":8,"area":"lr"},{"id":"2604.14164","title":"How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data","created":"2026-03-23","cited_by_count":8,"area":"lr"},{"id":"2604.26573","title":"PAINT: Partial-Solution Adaptive Interpolated Training for Self-Distilled Reasoners","created":"2026-04-29","cited_by_count":8,"area":"lr"},{"id":"2605.19433","title":"Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation","created":"2026-05-19","cited_by_count":8,"area":"lr"},{"id":"2508.15202","title":"Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models","created":"2025-08-21","cited_by_count":7,"area":"lr"},{"id":"2509.01649","title":"Distilled Pretraining: A modern lens of Data, In-Context Learning and Test-Time Scaling","created":"2025-09-01","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":"2604.01348","title":"Procedural Knowledge at Scale Improves Reasoning","created":"2026-04-01","cited_by_count":7,"area":"lr"},{"id":"2604.22074","title":"Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning","created":"2026-04-23","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":"2608.06243","title":"DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models","created":"2026-08-06","cited_by_count":7,"area":"lr"},{"id":"2506.09967","title":"Resa: Transparent Reasoning Models via SAEs","created":"2025-06-11","cited_by_count":6,"area":"lr"},{"id":"2507.16802","title":"Agentar-Fin-R1: Enhancing Financial Intelligence through Domain Expertise, Training Efficiency, and Advanced Reasoning","created":"2025-07-22","cited_by_count":6,"area":"lr"},{"id":"2507.18014","title":"Predictive Scaling Laws for Efficient GRPO Training of Large Reasoning Models","created":"2025-07-24","cited_by_count":6,"area":"lr"},{"id":"2508.12726","title":"DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM Reasoning","created":"2025-08-18","cited_by_count":6,"area":"lr"},{"id":"2509.21070","title":"ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning","created":"2025-09-25","cited_by_count":6,"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":"2512.04558","title":"On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference","created":"2025-12-04","cited_by_count":6,"area":"lr"},{"id":"2512.20908","title":"Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation","created":"2025-12-24","cited_by_count":6,"area":"lr"},{"id":"2510.06410","title":"Off-Trajectory Reasoning: Can LLMs Collaborate on Reasoning Trajectory?","created":"2025-10-07","cited_by_count":5,"area":"lr"},{"id":"2511.04694","title":"Reasoning Up the Instruction Ladder for Controllable Language Models","created":"2025-10-30","cited_by_count":5,"area":"lr"},{"id":"2512.01020","title":"Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics","created":"2025-11-30","cited_by_count":5,"area":"lr"},{"id":"2512.03783","title":"Omni-AutoThink: Adaptive Multimodal Reasoning via Reinforcement Learning","created":"2025-12-03","cited_by_count":5,"area":"lr"},{"id":"2512.21002","title":"Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation","created":"2025-12-24","cited_by_count":5,"area":"lr"},{"id":"2601.11517","title":"Do explanations generalize across large reasoning models?","created":"2026-01-16","cited_by_count":5,"area":"lr"},{"id":"2602.02581","title":"QuantLRM: Quantization of Large Reasoning Models via Fine-Tuning Signals","created":"2026-01-31","cited_by_count":5,"area":"lr"},{"id":"2603.04948","title":"$\\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space","created":"2026-03-05","cited_by_count":5,"area":"lr"},{"id":"2605.03314","title":"When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning","created":"2026-05-05","cited_by_count":5,"area":"lr"},{"id":"2606.05402","title":"ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces","created":"2026-06-03","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":"2509.20186","title":"Thinking Augmented Pre-training","created":"2025-09-24","cited_by_count":4,"area":"lr"},{"id":"2510.02272","title":"Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective","created":"2025-10-02","cited_by_count":4,"area":"lr"},{"id":"2510.11919","title":"LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens","created":"2025-10-13","cited_by_count":4,"area":"lr"},{"id":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4,"area":"lr"},{"id":"2601.01562","title":"Logics-STEM: Empowering LLM Reasoning via Failure-Driven Post-Training and Document Knowledge Enhancement","created":"2026-01-04","cited_by_count":4,"area":"lr"},{"id":"2601.06002","title":"The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning","created":"2026-01-09","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":"2602.08321","title":"Improving Data and Reward Design for Scientific Reasoning in Large Language Models","created":"2026-02-09","cited_by_count":4,"area":"lr"}],"next_cursor":"100"}