{"total":132,"rows":[{"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":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2503.01307","title":"Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs","created":"2025-03-03","cited_by_count":377,"area":"lr"},{"id":"2506.06941","title":"The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity","created":"2025-06-07","cited_by_count":302,"area":"lr"},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"area":"lr"},{"id":"2504.09858","title":"Reasoning Models Can Be Effective Without Thinking","created":"2025-04-14","cited_by_count":187,"area":"lr"},{"id":"2507.19849","title":"Agentic Reinforced Policy Optimization","created":"2025-07-26","cited_by_count":172,"area":"lr"},{"id":"2503.21614","title":"A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond","created":"2025-03-27","cited_by_count":132,"area":"lr"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2504.16828","title":"Process Reward Models That Think","created":"2025-04-23","cited_by_count":118,"area":"lr"},{"id":"2504.01943","title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding","created":"2025-04-02","cited_by_count":113,"area":"lr"},{"id":"2502.17387","title":"Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models","created":"2025-02-24","cited_by_count":109,"area":"lr"},{"id":"2502.14382","title":"S*: Test Time Scaling for Code Generation","created":"2025-02-20","cited_by_count":98,"area":"lr"},{"id":"2504.12329","title":"Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time","created":"2025-04-12","cited_by_count":48,"area":"lr"},{"id":"2503.19551","title":"Scaling Laws of Synthetic Data for Language Models","created":"2025-03-25","cited_by_count":46,"area":"synth"},{"id":"2505.20674","title":"PonderLM: Pretraining Language Models to Ponder in Continuous Space","created":"2025-05-27","cited_by_count":44,"area":null},{"id":"2504.04022","title":"Rethinking Reflection in Pre-Training","created":"2025-04-05","cited_by_count":43,"area":"lr"},{"id":"2505.13775","title":"Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens","created":"2025-05-19","cited_by_count":41,"area":"lr"},{"id":"2505.22334","title":"Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start","created":"2025-05-28","cited_by_count":41,"area":"lr"},{"id":"2604.01193","title":"Embarrassingly Simple Self-Distillation Improves Code Generation","created":"2026-04-01","cited_by_count":40,"area":"distill"},{"id":"2507.15778","title":"Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR","created":"2025-07-21","cited_by_count":39,"area":"lr"},{"id":"2504.09762","title":"Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!","created":"2025-04-14","cited_by_count":37,"area":"lr"},{"id":"2509.19803","title":"VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models","created":"2025-09-24","cited_by_count":36,"area":"lr"},{"id":"2505.12886","title":"Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective","created":"2025-05-19","cited_by_count":34,"area":"lr"},{"id":"2504.18875","title":"Generative to Agentic AI: Survey, Conceptualization, and Challenges","created":"2025-04-26","cited_by_count":33,"area":"agents"},{"id":"2506.05744","title":"Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties","created":"2025-06-06","cited_by_count":29,"area":"lr"},{"id":"2505.14604","title":"Let LRMs Break Free from Overthinking via Self-Braking Tuning","created":"2025-05-20","cited_by_count":27,"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":"2507.09075","title":"OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique","created":"2025-07-11","cited_by_count":25,"area":"lr"},{"id":"2510.13554","title":"Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization","created":"2025-10-15","cited_by_count":25,"area":"lr"},{"id":"2506.11474","title":"Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards","created":"2025-06-13","cited_by_count":24,"area":"lr"},{"id":"2505.16135","title":"Sudoku-Bench: Evaluating creative reasoning with Sudoku variants","created":"2025-05-22","cited_by_count":22,"area":"lr"},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2504.11741","title":"Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT?","created":"2025-04-16","cited_by_count":21,"area":"lr"},{"id":"2505.22148","title":"What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning","created":"2025-05-28","cited_by_count":21,"area":"lr"},{"id":"2503.17979","title":"Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities","created":"2025-03-23","cited_by_count":20,"area":"lr"},{"id":"2509.22485","title":"Group Critical-token Policy Optimization for Autoregressive Image Generation","created":"2025-09-26","cited_by_count":17,"area":null},{"id":"2603.07084","title":"Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR","created":"2026-03-07","cited_by_count":17,"area":"alignment"},{"id":"2509.23184","title":"PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space","created":"2025-09-27","cited_by_count":16,"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":"2505.19187","title":"LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling","created":"2025-05-25","cited_by_count":15,"area":"lr"},{"id":"2506.12860","title":"QFFT, Question-Free Fine-Tuning for Adaptive Reasoning","created":"2025-06-15","cited_by_count":15,"area":"lr"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2506.01748","title":"Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning","created":"2025-06-02","cited_by_count":14,"area":"lr"},{"id":"2505.17697","title":"Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models","created":"2025-05-23","cited_by_count":13,"area":"lr"},{"id":"2505.21825","title":"Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones","created":"2025-05-27","cited_by_count":13,"area":"lr"},{"id":"2506.07851","title":"Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning","created":"2025-06-09","cited_by_count":13,"area":"inference"},{"id":"2506.18841","title":"LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning","created":"2025-06-23","cited_by_count":13,"area":null},{"id":"2507.00417","title":"ASTRO: Teaching Language Models to Reason by Reflecting and Backtracking In-Context","created":"2025-07-01","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":"2503.16400","title":"ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos","created":"2025-03-20","cited_by_count":12,"area":"diffusion"},{"id":"2503.18069","title":"Long Is More Important Than Difficult for Training Reasoning Models","created":"2025-03-23","cited_by_count":11,"area":"lr"},{"id":"2505.16142","title":"RLKD: Distilling LLMs' Reasoning via Reinforcement Learning","created":"2025-05-22","cited_by_count":11,"area":"lr"},{"id":"2510.25992","title":"Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning","created":"2025-10-29","cited_by_count":11,"area":"lr"},{"id":"2512.07533","title":"VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection","created":"2025-12-08","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":"2504.10368","title":"Exploring the System 1 Thinking Capability of Large Reasoning Models","created":"2025-04-14","cited_by_count":10,"area":"lr"},{"id":"2506.08388","title":"Reinforcement Learning Teachers of Test Time Scaling","created":"2025-06-10","cited_by_count":10,"area":"lr"},{"id":"2503.19326","title":"Process or Result? Manipulated Ending Tokens Can Mislead Reasoning LLMs to Ignore the Correct Reasoning Steps","created":"2025-03-25","cited_by_count":9,"area":"lr"},{"id":"2505.00016","title":"Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning","created":"2025-04-23","cited_by_count":9,"area":"lr"},{"id":"2507.00726","title":"Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess","created":"2025-07-01","cited_by_count":9,"area":"lr"},{"id":"2509.07339","title":"Performative Thinking? The Brittle Correlation Between CoT Length and Problem Complexity","created":"2025-09-09","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":"2510.12680","title":"Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?","created":"2025-10-14","cited_by_count":9,"area":"lr"},{"id":"2507.16814","title":"Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning","created":"2025-07-22","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":"2505.10846","title":"AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models","created":"2025-05-16","cited_by_count":7,"area":"lr"},{"id":"2505.17315","title":"Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2509.24945","title":"MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes","created":"2025-09-29","cited_by_count":7,"area":"lr"},{"id":"2505.14403","title":"Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning","created":"2025-05-20","cited_by_count":6,"area":"lr"},{"id":"2506.12217","title":"From Emergence to Control: Probing and Modulating Self-Reflection in Language Models","created":"2025-06-13","cited_by_count":6,"area":null},{"id":"2506.23908","title":"Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence","created":"2025-06-30","cited_by_count":6,"area":"lr"},{"id":"2505.15508","title":"Multilingual Test-Time Scaling via Initial Thought Transfer","created":"2025-05-21","cited_by_count":5,"area":"lr"},{"id":"2507.02663","title":"Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models","created":"2025-07-03","cited_by_count":5,"area":"lr"},{"id":"2509.21499","title":"On Code-Induced Reasoning in LLMs","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2512.00831","title":"ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning","created":"2025-11-30","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":"2601.04611","title":"Character-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVR","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2601.04992","title":"Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization","created":"2026-01-08","cited_by_count":5,"area":"lr"},{"id":"2505.13718","title":"Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings","created":"2025-05-19","cited_by_count":4,"area":"lr"},{"id":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2508.03018","title":"Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning","created":"2025-08-05","cited_by_count":4,"area":"lr"},{"id":"2508.21051","title":"Language Models and Logic Programs for Trustworthy Tax Reasoning","created":"2025-08-28","cited_by_count":4,"area":"lr"},{"id":"2510.08203","title":"Memory Retrieval and Consolidation in Large Language Models through Function Tokens","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2510.09354","title":"Logit Arithmetic Elicits Long Reasoning Capabilities Without Training","created":"2025-10-10","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":"2604.04720","title":"What Makes Good Multilingual Reasoning? Disentangling Traces with Measurable Features","created":"2026-04-06","cited_by_count":4,"area":"lr"},{"id":"2505.17348","title":"DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic","created":"2025-05-22","cited_by_count":3,"area":"lr"},{"id":"2505.22131","title":"Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection","created":"2025-05-28","cited_by_count":3,"area":"lr"},{"id":"2507.09850","title":"The Challenge of Teaching Reasoning to LLMs Without RL or Distillation","created":"2025-07-14","cited_by_count":3,"area":"lr"},{"id":"2510.00319","title":"DecepChain: Inducing Deceptive Reasoning in Large Language Models","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2602.09276","title":"Effective Reasoning Chains Reduce Intrinsic Dimensionality","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2604.27201","title":"Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation","created":"2026-04-29","cited_by_count":3,"area":"lr"},{"id":"2606.10646","title":"How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2505.14684","title":"Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought Tuning","created":"2025-05-20","cited_by_count":2,"area":"lr"},{"id":"2506.03077","title":"StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2507.05362","title":"On the Bias of Next-Token Predictors Toward Systematically Inefficient Reasoning: A Shortest-Path Case Study","created":"2025-07-07","cited_by_count":2,"area":"lr"},{"id":"2507.11408","title":"KisMATH: Do LLMs Have Knowledge of Implicit Structures in Mathematical Reasoning?","created":"2025-07-15","cited_by_count":2,"area":"lr"},{"id":"2507.12759","title":"Logit Arithmetic Elicits Long Reasoning Capabilities Without Training","created":"2025-07-17","cited_by_count":2,"area":"lr"},{"id":"2510.06101","title":"The Valley of Code Reasoning: Scaling Knowledge Distillation of Large Language Models","created":"2025-10-07","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}