{"total":74,"rows":[{"id":"2504.13958","title":"ToolRL: Reward is All Tool Learning Needs","created":"2025-04-16","cited_by_count":362,"area":"agents"},{"id":"2504.11456","title":"DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning","created":"2025-04-15","cited_by_count":280,"area":"lr"},{"id":"2504.21318","title":"Phi-4-reasoning Technical Report","created":"2025-04-30","cited_by_count":151,"area":"lr"},{"id":"2504.02546","title":"GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning","created":"2025-04-03","cited_by_count":150,"area":"lr"},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"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":"2603.11137","title":"Scaling Reasoning Efficiently via Relaxed On-Policy Distillation","created":"2026-03-11","cited_by_count":82,"area":"lr"},{"id":"2505.10832","title":"Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL","created":"2025-05-16","cited_by_count":62,"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":"2508.03686","title":"CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward","created":"2025-08-05","cited_by_count":40,"area":"alignment"},{"id":"2505.20315","title":"Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL","created":"2025-05-22","cited_by_count":38,"area":"lr"},{"id":"2504.15777","title":"Tina: Tiny Reasoning Models via LoRA","created":"2025-04-22","cited_by_count":25,"area":"lr"},{"id":"2508.00410","title":"Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models","created":"2025-08-01","cited_by_count":23,"area":"lr"},{"id":"2505.16826","title":"KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning","created":"2025-05-22","cited_by_count":19,"area":"lr"},{"id":"2507.04103","title":"How to Train Your LLM Web Agent: A Statistical Diagnosis","created":"2025-07-05","cited_by_count":19,"area":"agents"},{"id":"2508.05612","title":"Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle","created":"2025-08-07","cited_by_count":19,"area":"lr"},{"id":"2505.09655","title":"DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning","created":"2025-05-14","cited_by_count":18,"area":"lr"},{"id":"2505.20013","title":"WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback","created":"2025-05-26","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":"2506.07736","title":"RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards","created":"2025-06-09","cited_by_count":14,"area":"lr"},{"id":"2507.06892","title":"Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model","created":"2025-07-09","cited_by_count":14,"area":"lr"},{"id":"2509.01684","title":"Reinforcement Learning for Machine Learning Engineering Agents","created":"2025-09-01","cited_by_count":14,"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":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"id":"2509.25454","title":"DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search","created":"2025-09-29","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":"2508.13023","title":"G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance","created":"2025-08-18","cited_by_count":10,"area":"lr"},{"id":"2509.21154","title":"GRPO is Secretly a Process Reward Model","created":"2025-09-25","cited_by_count":10,"area":"lr"},{"id":"2606.01281","title":"RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning","created":"2026-05-31","cited_by_count":9,"area":"lr"},{"id":"2509.06608","title":"Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors","created":"2025-09-08","cited_by_count":8,"area":"lr"},{"id":"2602.11779","title":"Temperature as a Meta-Policy: Adaptive Temperature in LLM Reinforcement Learning","created":"2026-02-12","cited_by_count":8,"area":null},{"id":"2506.09967","title":"Resa: Transparent Reasoning Models via SAEs","created":"2025-06-11","cited_by_count":6,"area":"lr"},{"id":"2508.05928","title":"Mitigating Think-Answer Mismatch in LLM Reasoning Through Noise-Aware Advantage Reweighting","created":"2025-08-08","cited_by_count":6,"area":"lr"},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2510.06410","title":"Off-Trajectory Reasoning: Can LLMs Collaborate on Reasoning Trajectory?","created":"2025-10-07","cited_by_count":5,"area":"lr"},{"id":"2509.18076","title":"Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates","created":"2025-09-22","cited_by_count":4,"area":"lr"},{"id":"2510.09354","title":"Logit Arithmetic Elicits Long Reasoning Capabilities Without Training","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2512.11816","title":"Reinforcement Learning for Latent-Space Thinking in LLMs","created":"2025-11-26","cited_by_count":4,"area":"lr"},{"id":"2601.23058","title":"From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement Learning","created":"2026-01-30","cited_by_count":4,"area":"lr"},{"id":"2603.04124","title":"BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning","created":"2026-03-04","cited_by_count":4,"area":"lr"},{"id":"2505.14264","title":"AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin","created":"2025-05-20","cited_by_count":3,"area":"lr"},{"id":"2506.03295","title":"Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem","created":"2025-06-03","cited_by_count":3,"area":"lr"},{"id":"2506.04734","title":"Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design","created":"2025-06-05","cited_by_count":3,"area":"lr"},{"id":"2506.13404","title":"Effective Learning for Small Reasoning Models: An Empirical Study on 0.5B Reasoning LLMs","created":"2025-06-16","cited_by_count":3,"area":"lr"},{"id":"2605.06241","title":"Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning","created":"2026-05-07","cited_by_count":3,"area":"lr"},{"id":"2506.21285","title":"Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning","created":"2025-06-26","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":"2601.09085","title":"MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2601.19404","title":"RPO:Reinforcement Fine-Tuning with Partial Reasoning Optimization","created":"2026-01-27","cited_by_count":2,"area":"lr"},{"id":"2601.19620","title":"R^3: Replay, Reflection, and Ranking Rewards for LLM Reinforcement Learning","created":"2026-01-27","cited_by_count":2,"area":"lr"},{"id":"2507.05065","title":"Replacing thinking with tool usage enables reasoning in small language models","created":"2025-07-07","cited_by_count":1,"area":"lr"},{"id":"2510.19171","title":"Think Straight, Stop Smart: Structured Reasoning for Efficient Multi-Hop RAG","created":"2025-10-22","cited_by_count":1,"area":"rag"},{"id":"2601.06677","title":"Plasticity vs. Rigidity: The Impact of Low-Rank Adapters on Reasoning on a Micro-Budget","created":"2026-01-10","cited_by_count":1,"area":"lr"},{"id":"2602.03022","title":"STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling Models","created":"2026-02-03","cited_by_count":1,"area":"agents"},{"id":"2604.14847","title":"TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models","created":"2026-04-16","cited_by_count":1,"area":"lr"},{"id":"2605.03195","title":"Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?","created":"2026-05-04","cited_by_count":1,"area":"agents"},{"id":"2606.06475","title":"RREDCoT: Segment-Level Reward Redistribution for Reasoning Models","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2505.00831","title":"SmallPlan: Leverage Small Language Models for Sequential Path Planning with Simulation-Powered, LLM-Guided Distillation","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2510.25065","title":"Rewarding Structural Conformance of Reasoning using Process Mining","created":"2025-10-29","cited_by_count":0,"area":"lr"},{"id":"2512.14761","title":"CAPE: Capability Achievement via Policy Execution","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2602.05946","title":"f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment","created":"2026-02-05","cited_by_count":0,"area":"lr"},{"id":"2603.16867","title":"Efficient Reasoning on the Edge","created":"2026-03-17","cited_by_count":0,"area":"lr"},{"id":"2604.18381","title":"Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.00199","title":"RSAT: Structured Attribution Makes Small Language Models Faithful Table Reasoners","created":"2026-04-30","cited_by_count":0,"area":"lr"},{"id":"2605.11538","title":"Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.17037","title":"D$^2$Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning","created":"2026-05-16","cited_by_count":0,"area":"lr"},{"id":"2606.09052","title":"INFUSER: Influence-Guided Self-Evolution Improves Reasoning","created":"2026-06-08","cited_by_count":0,"area":"lr"},{"id":"2606.30813","title":"Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.18006","title":"MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2608.10714","title":"Conversational Orchestration for Organic 6G","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.09425","title":"Edu-QuRating: Multi-Dimensional Educational Data Curation with Distilled Pairwise Judgements","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.36750","title":"Group-Marginalized Self-Rewarding RL Drives Zero-Label Self-Evolving","created":"2026-09-29","cited_by_count":0,"area":"synth"},{"id":"2610.01080","title":"Improving Math Reasoning through Value-guided Informative Search","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.04978","title":"What Will Post-Training Fix? Per-Problem Gains Are Shared Across Independent RL Runs, and Existing Checkpoints Predict Them Better Than A Priori Signals","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}