{"total":416,"rows":[{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664,"area":"lr"},{"id":"2401.15077","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","created":"2024-01-26","cited_by_count":578,"area":"lr"},{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559,"area":"lr"},{"id":"2601.18734","title":"Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models","created":"2026-01-26","cited_by_count":455,"area":"lr"},{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344,"area":"lr"},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2212.10071","title":"Large Language Models Are Reasoning Teachers","created":"2022-12-20","cited_by_count":329,"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":"2212.08410","title":"Teaching Small Language Models to Reason","created":"2022-12-16","cited_by_count":284,"area":"lr"},{"id":"2309.17452","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","created":"2023-09-29","cited_by_count":282,"area":"lr"},{"id":"2410.08146","title":"Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning","created":"2024-10-10","cited_by_count":279,"area":"lr"},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"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":"2311.01460","title":"Implicit Chain of Thought Reasoning via Knowledge Distillation","created":"2023-11-02","cited_by_count":176,"area":"lr"},{"id":"2407.06023","title":"Distilling System 2 into System 1","created":"2024-07-08","cited_by_count":159,"area":"lr"},{"id":"2212.00193","title":"Distilling Reasoning Capabilities into Smaller Language Models","created":"2022-12-01","cited_by_count":158,"area":"lr"},{"id":"2310.03731","title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","created":"2023-10-05","cited_by_count":156,"area":"lr"},{"id":"2306.14050","title":"Symbolic Chain-of-Thought Distillation: Small Models Can Also \"Think\" Step-by-Step","created":"2023-06-24","cited_by_count":148,"area":"lr"},{"id":"2303.12501","title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval","created":"2023-03-22","cited_by_count":132,"area":"lr"},{"id":"2502.07374","title":"LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!","created":"2025-02-11","cited_by_count":132,"area":"lr"},{"id":"2312.13558","title":"The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction","created":"2023-12-21","cited_by_count":123,"area":"lr"},{"id":"2506.03135","title":"OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models","created":"2025-06-03","cited_by_count":114,"area":"lr"},{"id":"2502.12143","title":"Small Models Struggle to Learn from Strong Reasoners","created":"2025-02-17","cited_by_count":113,"area":"lr"},{"id":"2505.13379","title":"Thinkless: LLM Learns When to Think","created":"2025-05-19","cited_by_count":113,"area":"lr"},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"area":"lr"},{"id":"2411.16489","title":"O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?","created":"2024-11-25","cited_by_count":92,"area":"lr"},{"id":"2401.08190","title":"MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline","created":"2024-01-16","cited_by_count":81,"area":"lr"},{"id":"2604.02288","title":"Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing","created":"2026-04-02","cited_by_count":76,"area":"lr"},{"id":"2502.08606","title":"Distillation Scaling Laws","created":"2025-02-12","cited_by_count":67,"area":"lr"},{"id":"2404.02657","title":"Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models","created":"2024-04-03","cited_by_count":65,"area":"lr"},{"id":"2503.01422","title":"Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding","created":"2025-03-03","cited_by_count":63,"area":"lr"},{"id":"2408.16737","title":"Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling","created":"2024-08-29","cited_by_count":61,"area":"lr"},{"id":"2506.17238","title":"Training a Scientific Reasoning Model for Chemistry","created":"2025-06-04","cited_by_count":56,"area":"lr"},{"id":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"area":"lr"},{"id":"2402.00658","title":"Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing","created":"2024-02-01","cited_by_count":49,"area":"lr"},{"id":"2402.04616","title":"Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation","created":"2024-02-07","cited_by_count":47,"area":"lr"},{"id":"2505.17612","title":"Distilling LLM Agent into Small Models with Retrieval and Code Tools","created":"2025-05-23","cited_by_count":47,"area":"lr"},{"id":"2406.15673","title":"Large Language Models have Intrinsic Self-Correction Ability","created":"2024-06-21","cited_by_count":46,"area":"lr"},{"id":"2402.01620","title":"MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models","created":"2024-02-02","cited_by_count":43,"area":"lr"},{"id":"2503.16385","title":"Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation","created":"2025-03-20","cited_by_count":43,"area":"lr"},{"id":"2602.15902","title":"Doc-to-LoRA: Learning to Instantly Internalize Contexts","created":"2026-02-13","cited_by_count":43,"area":"lr"},{"id":"2604.10688","title":"SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting","created":"2026-04-12","cited_by_count":43,"area":"lr"},{"id":"2412.14959","title":"Understanding the Dark Side of LLMs' Intrinsic Self-Correction","created":"2024-12-19","cited_by_count":42,"area":"lr"},{"id":"2603.23871","title":"HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation","created":"2026-03-25","cited_by_count":42,"area":"lr"},{"id":"2506.02208","title":"KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning","created":"2025-06-02","cited_by_count":41,"area":"lr"},{"id":"2502.06737","title":"VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data","created":"2025-02-10","cited_by_count":40,"area":"lr"},{"id":"2506.04301","title":"The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective","created":"2025-06-04","cited_by_count":39,"area":"lr"},{"id":"2607.05184","title":"Rethinking On-Policy Self-Distillation for Thinking Models","created":"2026-07-06","cited_by_count":39,"area":"lr"},{"id":"2501.03035","title":"Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning","created":"2025-01-06","cited_by_count":37,"area":"lr"},{"id":"2503.17523","title":"Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models","created":"2025-03-21","cited_by_count":37,"area":"lr"},{"id":"2502.08524","title":"LLM Pretraining with Continuous Concepts","created":"2025-02-12","cited_by_count":36,"area":"lr"},{"id":"2410.12735","title":"CREAM: Consistency Regularized Self-Rewarding Language Models","created":"2024-10-16","cited_by_count":35,"area":"lr"},{"id":"2501.06458","title":"O1 Replication Journey -- Part 3: Inference-time Scaling for Medical Reasoning","created":"2025-01-11","cited_by_count":35,"area":"lr"},{"id":"2602.22495","title":"Reinforcement-aware Knowledge Distillation for LLM Reasoning","created":"2026-02-26","cited_by_count":35,"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":"2312.07399","title":"Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales","created":"2023-12-12","cited_by_count":33,"area":"lr"},{"id":"2606.02684","title":"Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation","created":"2026-06-01","cited_by_count":32,"area":"lr"},{"id":"2410.18798","title":"Distill Visual Chart Reasoning Ability from LLMs to MLLMs","created":"2024-10-24","cited_by_count":31,"area":"lr"},{"id":"2502.13458","title":"ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails","created":"2025-02-19","cited_by_count":31,"area":"lr"},{"id":"2510.23497","title":"VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation","created":"2025-10-27","cited_by_count":31,"area":"lr"},{"id":"2607.02234","title":"Purified OPSD: On-Policy Self-Distillation Without Losing How to Think","created":"2026-07-02","cited_by_count":31,"area":"lr"},{"id":"2305.13888","title":"PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning","created":"2023-05-23","cited_by_count":29,"area":"lr"},{"id":"2411.19865","title":"Reverse Thinking Makes LLMs Stronger Reasoners","created":"2024-11-29","cited_by_count":29,"area":"lr"},{"id":"2310.14747","title":"MCC-KD: Multi-CoT Consistent Knowledge Distillation","created":"2023-10-23","cited_by_count":28,"area":"lr"},{"id":"2506.05345","title":"Inference-Time Hyper-Scaling with KV Cache Compression","created":"2025-06-05","cited_by_count":27,"area":"lr"},{"id":"2605.07804","title":"Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning","created":"2026-05-08","cited_by_count":27,"area":"lr"},{"id":"2503.03730","title":"Towards Understanding Distilled Reasoning Models: A Representational Approach","created":"2025-03-05","cited_by_count":26,"area":"lr"},{"id":"2606.22600","title":"On the Position Bias of On-Policy Distillation","created":"2026-06-21","cited_by_count":26,"area":"lr"},{"id":"2605.10889","title":"Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why","created":"2026-05-11","cited_by_count":25,"area":"lr"},{"id":"2309.13182","title":"Effective Distillation of Table-based Reasoning Ability from LLMs","created":"2023-09-22","cited_by_count":23,"area":"lr"},{"id":"2310.07999","title":"LEMON: Lossless model expansion","created":"2023-10-12","cited_by_count":23,"area":"lr"},{"id":"2403.03348","title":"Learning to Maximize Mutual Information for Chain-of-Thought Distillation","created":"2024-03-05","cited_by_count":23,"area":"lr"},{"id":"2405.16064","title":"Keypoint-based Progressive Chain-of-Thought Distillation for LLMs","created":"2024-05-25","cited_by_count":23,"area":"lr"},{"id":"2412.01282","title":"Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement","created":"2024-12-02","cited_by_count":23,"area":"lr"},{"id":"2510.00553","title":"On Predictability of Reinforcement Learning Dynamics for Large Language Models","created":"2025-10-01","cited_by_count":23,"area":"lr"},{"id":"2408.06276","title":"Review-driven Personalized Preference Reasoning with Large Language Models for Recommendation","created":"2024-08-12","cited_by_count":22,"area":"lr"},{"id":"2502.20339","title":"Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners","created":"2025-02-27","cited_by_count":22,"area":"lr"},{"id":"2504.10449","title":"M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models","created":"2025-04-14","cited_by_count":21,"area":"lr"},{"id":"2312.10730","title":"Mixed Distillation Helps Smaller Language Model Better Reasoning","created":"2023-12-17","cited_by_count":19,"area":"lr"},{"id":"2403.16385","title":"Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA","created":"2024-03-25","cited_by_count":19,"area":"lr"},{"id":"2608.19098","title":"Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation","created":"2026-08-19","cited_by_count":18,"area":"lr"},{"id":"2409.01281","title":"Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs","created":"2024-08-25","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":"2605.28014","title":"ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains","created":"2026-05-27","cited_by_count":17,"area":"lr"},{"id":"2406.14511","title":"Investigating Mysteries of CoT-Augmented Distillation","created":"2024-06-20","cited_by_count":16,"area":"lr"},{"id":"2505.15925","title":"VERDI: VLM-Embedded Reasoning for Autonomous Driving","created":"2025-05-21","cited_by_count":16,"area":"lr"},{"id":"2506.14948","title":"Structured Moral Reasoning in Language Models: A Value-Grounded Evaluation Framework","created":"2025-06-17","cited_by_count":16,"area":"lr"},{"id":"2603.13260","title":"Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation","created":"2026-02-25","cited_by_count":16,"area":"lr"},{"id":"2606.18974","title":"Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning","created":"2026-06-17","cited_by_count":16,"area":"lr"},{"id":"2312.05434","title":"Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models","created":"2023-12-09","cited_by_count":15,"area":"lr"},{"id":"2502.07191","title":"Bag of Tricks for Inference-time Computation of LLM Reasoning","created":"2025-02-11","cited_by_count":15,"area":"lr"},{"id":"2510.04265","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","created":"2025-10-05","cited_by_count":15,"area":"lr"},{"id":"2405.19737","title":"Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation","created":"2024-05-30","cited_by_count":14,"area":"lr"},{"id":"2510.12184","title":"CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs","created":"2025-10-14","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":"2308.04679","title":"Sci-CoT: Leveraging Large Language Models for Enhanced Knowledge Distillation in Small Models for Scientific QA","created":"2023-08-09","cited_by_count":13,"area":"lr"},{"id":"2310.13332","title":"Democratizing Reasoning Ability: Tailored Learning from Large Language Model","created":"2023-10-20","cited_by_count":13,"area":"lr"},{"id":"2311.09214","title":"Mind's Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models","created":"2023-11-15","cited_by_count":13,"area":"lr"},{"id":"2402.16631","title":"GenAINet: Enabling Wireless Collective Intelligence via Knowledge Transfer and Reasoning","created":"2024-02-26","cited_by_count":13,"area":"lr"},{"id":"2404.09170","title":"Distilling Reasoning Ability from Large Language Models with Adaptive Thinking","created":"2024-04-14","cited_by_count":13,"area":"lr"}],"next_cursor":"100"}