{"total":77,"rows":[{"id":"2503.09516","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","created":"2025-03-12","cited_by_count":1444,"area":"lr"},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341,"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":"2503.24235","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":"2510.02283","title":"Self-Forcing++: Towards Minute-Scale High-Quality Video Generation","created":"2025-10-02","cited_by_count":192,"area":"diffusion"},{"id":"2502.11886","title":"LIMR: Less is More for RL Scaling","created":"2025-02-17","cited_by_count":139,"area":"lr"},{"id":"2508.10751","title":"Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models","created":"2025-08-14","cited_by_count":138,"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":"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":"2504.03380","title":"Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning","created":"2025-04-04","cited_by_count":104,"area":"lr"},{"id":"2502.14382","title":"S*: Test Time Scaling for Code Generation","created":"2025-02-20","cited_by_count":98,"area":"lr"},{"id":"2506.11902","title":"TreeRL: LLM Reinforcement Learning with On-Policy Tree Search","created":"2025-06-13","cited_by_count":80,"area":"alignment"},{"id":"2503.04548","title":"An Empirical Study on Eliciting and Improving R1-like Reasoning Models","created":"2025-03-06","cited_by_count":78,"area":"lr"},{"id":"2505.23646","title":"Are Reasoning Models More Prone to Hallucination?","created":"2025-05-29","cited_by_count":64,"area":"lr"},{"id":"2510.04206","title":"AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework","created":"2025-10-05","cited_by_count":62,"area":"agents"},{"id":"2504.06514","title":"Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?","created":"2025-04-09","cited_by_count":58,"area":"lr"},{"id":"2509.10446","title":"DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL","created":"2025-09-12","cited_by_count":55,"area":"agents"},{"id":"2502.12018","title":"Atom of Thoughts for Markov LLM Test-Time Scaling","created":"2025-02-17","cited_by_count":54,"area":"lr"},{"id":"2505.05408","title":"Crosslingual Reasoning through Test-Time Scaling","created":"2025-05-08","cited_by_count":46,"area":"lr"},{"id":"2505.20674","title":"PonderLM: Pretraining Language Models to Ponder in Continuous Space","created":"2025-05-27","cited_by_count":44,"area":null},{"id":"2509.18119","title":"MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents","created":"2025-09-10","cited_by_count":43,"area":"agents"},{"id":"2504.09772","title":"Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning","created":"2025-04-14","cited_by_count":29,"area":"lr"},{"id":"2506.13666","title":"We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems","created":"2025-06-16","cited_by_count":27,"area":"agents"},{"id":"2506.07636","title":"SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling","created":"2025-06-09","cited_by_count":26,"area":"agents"},{"id":"2504.07052","title":"To Backtrack or Not to Backtrack: When Sequential Search Limits Model Reasoning","created":"2025-04-09","cited_by_count":24,"area":"lr"},{"id":"2502.06773","title":"On the Emergence of Thinking in LLMs I: Searching for the Right Intuition","created":"2025-02-10","cited_by_count":22,"area":"lr"},{"id":"2505.19640","title":"Interleaved Reasoning for Large Language Models via Reinforcement Learning","created":"2025-05-26","cited_by_count":21,"area":"lr"},{"id":"2505.22960","title":"Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness","created":"2025-05-29","cited_by_count":20,"area":"lr"},{"id":"2505.02665","title":"A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law","created":"2025-05-05","cited_by_count":19,"area":"lr"},{"id":"2510.14807","title":"Beyond the Sampled Token: Preserving Candidate Support in RLVR","created":"2025-10-16","cited_by_count":18,"area":null},{"id":"2504.14350","title":"An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint","created":"2025-04-19","cited_by_count":17,"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":"2503.08525","title":"GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training","created":"2025-03-11","cited_by_count":14,"area":"lr"},{"id":"2505.19406","title":"Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model","created":"2025-05-26","cited_by_count":14,"area":"lr"},{"id":"2510.05837","title":"EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget","created":"2025-10-07","cited_by_count":14,"area":null},{"id":"2607.05378","title":"CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents","created":"2026-07-06","cited_by_count":14,"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":"2603.23183","title":"Reasoning over Semantic IDs Enhances Generative Recommendation","created":"2026-03-24","cited_by_count":13,"area":"lr"},{"id":"2510.00911","title":"RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training","created":"2025-10-01","cited_by_count":12,"area":"lr"},{"id":"2510.08141","title":"SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2602.03048","title":"CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs","created":"2026-02-03","cited_by_count":12,"area":"lr"},{"id":"2503.14495","title":"Temporal Consistency for LLM Reasoning Process Error Identification","created":"2025-03-18","cited_by_count":10,"area":"lr"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","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":"2507.00711","title":"Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectories","created":"2025-07-01","cited_by_count":10,"area":"lr"},{"id":"2510.05251","title":"Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning","created":"2025-10-06","cited_by_count":10,"area":"lr"},{"id":"2602.19895","title":"DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning","created":"2026-02-23","cited_by_count":9,"area":"lr"},{"id":"2506.20729","title":"Test-time Scaling Techniques in Theoretical Physics -- A Comparison of Methods on the TPBench Dataset","created":"2025-06-25","cited_by_count":8,"area":"lr"},{"id":"2602.12279","title":"UniT: Unified Multimodal Chain-of-Thought Test-time Scaling","created":"2026-02-12","cited_by_count":8,"area":"lr"},{"id":"2605.21125","title":"Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation","created":"2026-05-20","cited_by_count":7,"area":"lr"},{"id":"2601.03764","title":"Learning Shrinks the Hard Tail: Training-Dependent Inference Scaling in a Solvable Linear Model","created":"2026-01-07","cited_by_count":6,"area":null},{"id":"2502.20545","title":"SoS1: O1 and R1-Like Reasoning LLMs are Sum-of-Square Solvers","created":"2025-02-27","cited_by_count":5,"area":"lr"},{"id":"2510.22228","title":"When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs","created":"2025-10-25","cited_by_count":5,"area":"lr"},{"id":"2502.12022","title":"Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving","created":"2025-02-17","cited_by_count":4,"area":"lr"},{"id":"2504.09100","title":"A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directions","created":"2025-04-12","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":"2602.14868","title":"Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning","created":"2026-02-16","cited_by_count":4,"area":"lr"},{"id":"2504.18587","title":"An Expectation-Maximization Perspective on Reinforcement Learning for LLM Reasoning","created":"2025-04-24","cited_by_count":3,"area":"lr"},{"id":"2512.20061","title":"Scaling Reinforcement Learning for Content Moderation with Large Language Models","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2601.08000","title":"Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety","created":"2026-01-12","cited_by_count":3,"area":"lr"},{"id":"2604.14646","title":"Targeted Exploration via Unified Entropy Control for Reinforcement Learning","created":"2026-04-16","cited_by_count":3,"area":"lr"},{"id":"2605.18864","title":"SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs","created":"2026-05-15","cited_by_count":3,"area":"lr"},{"id":"2607.05861","title":"Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization","created":"2026-07-07","cited_by_count":3,"area":"lr"},{"id":"2510.21398","title":"Boosting Accuracy and Efficiency of Budget Forcing in LLMs via Reinforcement Learning for Mathematical Reasoning","created":"2025-10-24","cited_by_count":2,"area":"lr"},{"id":"2606.03698","title":"Multi$^2$: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2505.11140","title":"Follow the Path: Reasoning over Knowledge Graph Paths to Improve Large Language Model Factuality","created":"2025-05-16","cited_by_count":1,"area":"lr"},{"id":"2505.12951","title":"DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management","created":"2025-05-19","cited_by_count":1,"area":"lr"},{"id":"2508.10137","title":"mSCoRe: a $M$ultilingual and Scalable Benchmark for $S$kill-based $Co$mmonsense $Re$asoning","created":"2025-08-13","cited_by_count":1,"area":"lr"},{"id":"2508.10839","title":"Reinforced Language Models for Sequential Decision Making","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2508.17250","title":"Routing Distilled Knowledge via Mixture of LoRA Experts for Large Language Model based Bundle Generation","created":"2025-08-24","cited_by_count":1,"area":"distill"},{"id":"2509.09629","title":"Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems","created":"2025-09-11","cited_by_count":1,"area":"agents"},{"id":"2601.12730","title":"Distribution-Centric Policy Optimization Dominates Exploration-Exploitation Trade-off","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2603.22430","title":"Inference Time Policy Optimization for Offline RL with Differentiable World Models","created":"2026-03-23","cited_by_count":1,"area":"wm"},{"id":"2605.11461","title":"Breaking $\\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2510.27462","title":"VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision","created":"2025-10-31","cited_by_count":0,"area":"lr"},{"id":"2601.17467","title":"Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping","created":"2026-01-24","cited_by_count":0,"area":"lr"},{"id":"2603.18073","title":"Continually self-improving AI","created":"2026-03-18","cited_by_count":0,"area":"synth"}],"next_cursor":null}