{"total":139,"rows":[{"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":"2504.13958","title":"ToolRL: Reward is All Tool Learning Needs","created":"2025-04-16","cited_by_count":362,"area":"agents"},{"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":"2504.20571","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","created":"2025-04-29","cited_by_count":295,"area":"lr"},{"id":"2504.03160","title":"DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments","created":"2025-04-04","cited_by_count":286,"area":"lr"},{"id":"2504.16084","title":"TTRL: Test-Time Reinforcement Learning","created":"2025-04-22","cited_by_count":275,"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":"2506.21734","title":"Hierarchical Reasoning Model","created":"2025-06-26","cited_by_count":177,"area":"lr"},{"id":"2503.10460","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond","created":"2025-03-13","cited_by_count":175,"area":"lr"},{"id":"2503.23383","title":"ToRL: Scaling Tool-Integrated RL","created":"2025-03-30","cited_by_count":169,"area":"agents"},{"id":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2504.21318","title":"Phi-4-reasoning Technical Report","created":"2025-04-30","cited_by_count":151,"area":"lr"},{"id":"2506.02177","title":"Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts","created":"2025-06-02","cited_by_count":113,"area":"lr"},{"id":"2504.03380","title":"Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning","created":"2025-04-04","cited_by_count":104,"area":"lr"},{"id":"2504.05520","title":"Efficient Reinforcement Finetuning via Adaptive Curriculum Learning","created":"2025-04-07","cited_by_count":93,"area":"lr"},{"id":"2504.07086","title":"A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility","created":"2025-04-09","cited_by_count":93,"area":"lr"},{"id":"2505.12370","title":"Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning","created":"2025-05-18","cited_by_count":81,"area":"lr"},{"id":"2504.01903","title":"STAR-1: Safer Alignment of Reasoning LLMs with 1K Data","created":"2025-04-02","cited_by_count":68,"area":"lr"},{"id":"2506.05316","title":"Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay","created":"2025-06-05","cited_by_count":56,"area":"lr"},{"id":"2507.04632","title":"Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?","created":"2025-07-07","cited_by_count":52,"area":"lr"},{"id":"2506.08989","title":"SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning","created":"2025-06-10","cited_by_count":42,"area":"lr"},{"id":"2505.23433","title":"Diversity-Aware Policy Optimization for Large Language Model Reasoning","created":"2025-05-29","cited_by_count":41,"area":"lr"},{"id":"2505.13988","title":"The Hallucination Tax of Reinforcement Finetuning","created":"2025-05-20","cited_by_count":40,"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":"2503.24377","title":"Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models","created":"2025-03-31","cited_by_count":36,"area":"lr"},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2509.06948","title":"Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning","created":"2025-09-08","cited_by_count":30,"area":"lr"},{"id":"2506.09016","title":"SPEED-RL: Faster Training of Reasoning Models via Online Curriculum Learning","created":"2025-06-10","cited_by_count":29,"area":"lr"},{"id":"2509.25300","title":"Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning","created":"2025-09-29","cited_by_count":29,"area":"lr"},{"id":"2503.22230","title":"Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback","created":"2025-03-28","cited_by_count":26,"area":"alignment"},{"id":"2507.09884","title":"VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains","created":"2025-07-14","cited_by_count":24,"area":"lr"},{"id":"2609.04172","title":"Rethinking On-Policy Distillation of Large Language Models II: One Training Example","created":"2026-09-03","cited_by_count":24,"area":"distill"},{"id":"2505.24098","title":"HardTests: Synthesizing High-Quality Test Cases for LLM Coding","created":"2025-05-30","cited_by_count":23,"area":"lr"},{"id":"2504.16918","title":"OptimAI: Optimization from Natural Language Using LLM-Powered AI Agents","created":"2025-04-23","cited_by_count":22,"area":"agents"},{"id":"2504.02949","title":"VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning","created":"2025-04-03","cited_by_count":21,"area":null},{"id":"2511.05993","title":"Revisiting Entropy in Reinforcement Learning for Large Reasoning Models","created":"2025-11-08","cited_by_count":21,"area":"lr"},{"id":"2509.01321","title":"Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward","created":"2025-09-01","cited_by_count":19,"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":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2505.21067","title":"Why Distillation can Outperform Zero-RL: The Role of Flexible Reasoning","created":"2025-05-27","cited_by_count":15,"area":"lr"},{"id":"2602.01970","title":"Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models","created":"2026-02-02","cited_by_count":14,"area":"lr"},{"id":"2505.19850","title":"DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning","created":"2025-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2506.02096","title":"SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis","created":"2025-06-02","cited_by_count":12,"area":"lr"},{"id":"2510.24832","title":"Scheduling Your LLM Reinforcement Learning with Reasoning Trees","created":"2025-10-28","cited_by_count":12,"area":"lr"},{"id":"2510.26491","title":"Data-Efficient RLVR via Off-Policy Influence Guidance","created":"2025-10-30","cited_by_count":12,"area":"lr"},{"id":"2602.21492","title":"GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning","created":"2026-02-25","cited_by_count":12,"area":null},{"id":"2505.19281","title":"A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning","created":"2025-05-25","cited_by_count":11,"area":"deeprl"},{"id":"2505.19439","title":"Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers","created":"2025-05-26","cited_by_count":11,"area":"lr"},{"id":"2603.10887","title":"Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models","created":"2026-03-11","cited_by_count":11,"area":"lr"},{"id":"2506.08388","title":"Reinforcement Learning Teachers of Test Time Scaling","created":"2025-06-10","cited_by_count":10,"area":"lr"},{"id":"2507.06573","title":"From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization","created":"2025-07-09","cited_by_count":10,"area":"lr"},{"id":"2603.25184","title":"Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model","created":"2026-03-26","cited_by_count":10,"area":"lr"},{"id":"2606.11119","title":"TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning","created":"2026-06-09","cited_by_count":10,"area":"agents"},{"id":"2505.17652","title":"Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective","created":"2025-05-23","cited_by_count":9,"area":"lr"},{"id":"2505.22626","title":"SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning","created":"2025-05-28","cited_by_count":9,"area":"offlinerl"},{"id":"2506.11480","title":"LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment","created":"2025-06-13","cited_by_count":9,"area":"lr"},{"id":"2508.18914","title":"FormaRL: Enhancing Autoformalization with no Labeled Data","created":"2025-08-26","cited_by_count":9,"area":null},{"id":"2510.01459","title":"LSPO: Length-aware Dynamic Sampling for Policy Optimization in LLM Reasoning","created":"2025-10-01","cited_by_count":9,"area":"lr"},{"id":"2510.14321","title":"Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigm","created":"2025-10-16","cited_by_count":9,"area":"lr"},{"id":"2603.15500","title":"Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty","created":"2026-03-16","cited_by_count":9,"area":"lr"},{"id":"2505.20072","title":"Incentivizing Strong Reasoning from Weak Supervision","created":"2025-05-26","cited_by_count":8,"area":"lr"},{"id":"2506.07104","title":"How Far Are We from Optimal Reasoning Efficiency?","created":"2025-06-08","cited_by_count":8,"area":"lr"},{"id":"2508.20549","title":"MedGR$^2$: Breaking the Data Barrier for Medical Reasoning via Generative Reward Learning","created":"2025-08-28","cited_by_count":8,"area":"lr"},{"id":"2602.04735","title":"From Data to Behavior: Predicting Unintended Model Behaviors Before Training","created":"2026-02-04","cited_by_count":8,"area":null},{"id":"2602.07909","title":"SparseEval: Efficient Evaluation of Large Language Models by Sparse Optimization","created":"2026-02-08","cited_by_count":8,"area":null},{"id":"2603.21177","title":"Prompt replay: speeding up grpo with on-policy reuse of high-signal prompts","created":"2026-03-22","cited_by_count":8,"area":"lr"},{"id":"2505.17266","title":"Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2510.03865","title":"Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration","created":"2025-10-04","cited_by_count":7,"area":"lr"},{"id":"2512.13106","title":"TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning","created":"2025-12-15","cited_by_count":7,"area":"lr"},{"id":"2607.22002","title":"Learning as Reasoning Unfolds: Progressive Rollout Allocation for Efficient Reinforcement Learning","created":"2026-07-24","cited_by_count":7,"area":"lr"},{"id":"2505.03418","title":"Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey","created":"2025-05-06","cited_by_count":6,"area":"lr"},{"id":"2505.12457","title":"UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data Selection","created":"2025-05-18","cited_by_count":6,"area":"lr"},{"id":"2505.23118","title":"Elicit and Enhance: Advancing Multimodal Reasoning in Medical Scenarios","created":"2025-05-29","cited_by_count":6,"area":"lr"},{"id":"2506.08672","title":"RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling","created":"2025-06-10","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":"2603.01907","title":"Efficient RLVR Training via Weighted Mutual Information Data Selection","created":"2026-03-02","cited_by_count":6,"area":"alignment"},{"id":"2608.04001","title":"Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility","created":"2026-08-04","cited_by_count":6,"area":"lr"},{"id":"2506.18330","title":"Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics Learning","created":"2025-06-23","cited_by_count":5,"area":"lr"},{"id":"2510.06261","title":"AlphaApollo: A System for Deep Agentic Reasoning","created":"2025-10-05","cited_by_count":5,"area":"agents"},{"id":"2507.01951","title":"Test-Time Scaling with Reflective Generative Model","created":"2025-07-02","cited_by_count":4,"area":"lr"},{"id":"2508.05015","title":"SPaCe: Unlocking Sample-Efficient Large Language Models Training With Self-Pace Curriculum Learning","created":"2025-08-07","cited_by_count":4,"area":"lr"},{"id":"2510.04072","title":"Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"id":"2505.17988","title":"Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning","created":"2025-05-23","cited_by_count":3,"area":"lr"},{"id":"2508.10164","title":"Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization","created":"2025-08-13","cited_by_count":3,"area":"lr"},{"id":"2509.25762","title":"OPPO: Accelerating PPO-based RLHF via Pipeline Overlap","created":"2025-09-30","cited_by_count":3,"area":"alignment"},{"id":"2511.06307","title":"DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation","created":"2025-11-09","cited_by_count":3,"area":"lr"},{"id":"2602.07830","title":"Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning","created":"2026-02-08","cited_by_count":3,"area":"lr"},{"id":"2605.00015","title":"TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning","created":"2026-04-18","cited_by_count":3,"area":null},{"id":"2605.08441","title":"DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2506.00577","title":"Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs","created":"2025-05-31","cited_by_count":2,"area":"lr"},{"id":"2601.03111","title":"One Sample to Rule Them All: Extreme Data Efficiency in Multidiscipline Reasoning with Reinforcement Learning","created":"2026-01-06","cited_by_count":2,"area":"lr"},{"id":"2602.03452","title":"Beyond Variance: Prompt-Efficient RLVR via Rare-Event Amplification and Bidirectional Pairing","created":"2026-02-03","cited_by_count":2,"area":"lr"},{"id":"2603.03297","title":"TTSR: Test-Time Self-Evolving via Reflection","created":"2026-02-06","cited_by_count":2,"area":"synth"},{"id":"2603.13348","title":"AutoTool: Automatic Scaling of Tool-Use Capabilities in RL via Decoupled Entropy Constraints","created":"2026-03-07","cited_by_count":2,"area":"lr"},{"id":"2604.03993","title":"Can LLMs Learn to Reason Robustly under Noisy Supervision?","created":"2026-04-05","cited_by_count":2,"area":"lr"},{"id":"2605.09188","title":"DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation","created":"2026-05-09","cited_by_count":2,"area":"lr"},{"id":"2605.27354","title":"Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders","created":"2026-05-26","cited_by_count":2,"area":"mechinterp"},{"id":"2605.28631","title":"Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2607.26253","title":"Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR","created":"2026-07-28","cited_by_count":2,"area":null},{"id":"2607.27610","title":"Kalman Meets Curriculum: Efficient Dynamic Prompt Selection for Adaptive RL Finetuning","created":"2026-07-30","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}