{"total":78,"rows":[{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810,"area":"lr"},{"id":"2503.18892","title":"SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild","created":"2025-03-24","cited_by_count":511,"area":"lr"},{"id":"2504.11536","title":"ReTool: Reinforcement Learning for Strategic Tool Use in LLMs","created":"2025-04-15","cited_by_count":392,"area":"lr"},{"id":"2503.05592","title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","created":"2025-03-07","cited_by_count":336,"area":"lr"},{"id":"2504.21776","title":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability","created":"2025-04-30","cited_by_count":335,"area":"lr"},{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281,"area":"lr"},{"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":"2504.11468","title":"SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models","created":"2025-04-10","cited_by_count":212,"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":"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":"2508.05629","title":"On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification","created":"2025-08-07","cited_by_count":127,"area":"lr"},{"id":"2503.17352","title":"OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles","created":"2025-03-21","cited_by_count":124,"area":"lr"},{"id":"2509.01055","title":"VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use","created":"2025-09-01","cited_by_count":96,"area":"lr"},{"id":"2504.05520","title":"Efficient Reinforcement Finetuning via Adaptive Curriculum Learning","created":"2025-04-07","cited_by_count":93,"area":"lr"},{"id":"2504.13818","title":"Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning","created":"2025-04-18","cited_by_count":84,"area":"lr"},{"id":"2505.23564","title":"Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models","created":"2025-05-29","cited_by_count":75,"area":"lr"},{"id":"2505.15810","title":"GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents","created":"2025-05-21","cited_by_count":74,"area":"lr"},{"id":"2503.21380","title":"Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models","created":"2025-03-27","cited_by_count":70,"area":"lr"},{"id":"2504.14286","title":"SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM","created":"2025-04-19","cited_by_count":68,"area":"lr"},{"id":"2505.11274","title":"SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning","created":"2025-05-16","cited_by_count":48,"area":"lr"},{"id":"2506.08745","title":"Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning","created":"2025-06-10","cited_by_count":46,"area":"lr"},{"id":"2510.01135","title":"Prompt Curriculum Learning for Efficient LLM Post-Training","created":"2025-10-01","cited_by_count":45,"area":null},{"id":"2505.03469","title":"Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models","created":"2025-05-06","cited_by_count":39,"area":"lr"},{"id":"2505.20686","title":"Accelerating RL for LLM Reasoning with Optimal Advantage Regression","created":"2025-05-27","cited_by_count":24,"area":"lr"},{"id":"2505.24480","title":"Towards Effective Code-Integrated Reasoning","created":"2025-05-30","cited_by_count":23,"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":"2505.14107","title":"DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models","created":"2025-05-20","cited_by_count":21,"area":"lr"},{"id":"2508.02260","title":"Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning","created":"2025-08-04","cited_by_count":21,"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":"2505.24630","title":"Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models","created":"2025-05-30","cited_by_count":19,"area":"lr"},{"id":"2507.04607","title":"PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process","created":"2025-07-07","cited_by_count":18,"area":"lr"},{"id":"2512.20745","title":"AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent","created":"2025-12-23","cited_by_count":17,"area":"lr"},{"id":"2505.07787","title":"Learning from Peers in Reasoning Models","created":"2025-05-12","cited_by_count":16,"area":"lr"},{"id":"2505.12366","title":"DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization","created":"2025-05-18","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":"2506.09820","title":"CoRT: Code-integrated Reasoning within Thinking","created":"2025-06-11","cited_by_count":15,"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":"2505.24273","title":"How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning","created":"2025-05-30","cited_by_count":13,"area":"lr"},{"id":"2506.04894","title":"ICPC-Eval: Probing the Frontiers of LLM Reasoning with Competitive Programming Contests","created":"2025-06-05","cited_by_count":13,"area":"lr"},{"id":"2508.08401","title":"Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery","created":"2025-08-11","cited_by_count":12,"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":"2504.09627","title":"Slow Thinking for Sequential Recommendation","created":"2025-04-13","cited_by_count":11,"area":"lr"},{"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":"2506.07712","title":"Through the Valley: Path to Effective Long CoT Training for Small Language Models","created":"2025-06-09","cited_by_count":11,"area":"lr"},{"id":"2510.10959","title":"Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning","created":"2025-10-13","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":"2506.18485","title":"A Simple \"Motivation\" Can Enhance Reinforcement Finetuning of Large Reasoning Models","created":"2025-06-23","cited_by_count":7,"area":"lr"},{"id":"2508.05613","title":"Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models","created":"2025-08-07","cited_by_count":6,"area":"lr"},{"id":"2512.02874","title":"Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning","created":"2025-12-02","cited_by_count":6,"area":"lr"},{"id":"2510.20342","title":"Teaching Language Models to Reason with Tools","created":"2025-10-23","cited_by_count":5,"area":"lr"},{"id":"2506.23643","title":"Act-With-Think: Chunk Auto-Regressive Modeling for Generative Recommendation","created":"2025-06-30","cited_by_count":4,"area":"lr"},{"id":"2509.04027","title":"Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thought","created":"2025-09-04","cited_by_count":4,"area":"lr"},{"id":"2512.01925","title":"Rectifying LLM Thought from Lens of Optimization","created":"2025-12-01","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":"2604.11446","title":"Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration","created":"2026-04-13","cited_by_count":4,"area":null},{"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":"2509.14718","title":"ToolSample: Dual Dynamic Sampling Methods with Curriculum Learning for RL-based Tool Learning","created":"2025-09-18","cited_by_count":3,"area":"agents"},{"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":"2606.18388","title":"LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents","created":"2026-06-16","cited_by_count":3,"area":"agents"},{"id":"2505.16810","title":"DeepRec: Towards a Deep Dive Into the Item Space with Large Language Model Based Recommendation","created":"2025-05-22","cited_by_count":2,"area":"lr"},{"id":"2509.05007","title":"Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework","created":"2025-09-05","cited_by_count":2,"area":"lr"},{"id":"2512.15089","title":"Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models","created":"2025-12-17","cited_by_count":2,"area":"lr"},{"id":"2601.21711","title":"TACLer: Tailored Curriculum Reinforcement Learning for Efficient Reasoning","created":"2026-01-29","cited_by_count":2,"area":"lr"},{"id":"2602.01709","title":"ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2605.08817","title":"How You Begin is How You Reason: Driving Exploration in RLVR via Prefix-Tuned Priors","created":"2026-05-09","cited_by_count":2,"area":"lr"},{"id":"2605.09931","title":"PruneTIR: Inference-Time Tool Call Pruning for Effective yet Efficient Tool-Integrated Reasoning","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2606.08543","title":"PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR","created":"2026-06-07","cited_by_count":2,"area":"lr"},{"id":"2608.16798","title":"ClawGym II: Exploring Black-Box RL on Agent Harness","created":"2026-08-17","cited_by_count":2,"area":null},{"id":"2505.18467","title":"Pedagogy-R1: Pedagogically-Aligned Reasoning Model with Balanced Educational Benchmark","created":"2025-05-24","cited_by_count":1,"area":"lr"},{"id":"2604.14258","title":"GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2605.26971","title":"RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.10522","title":"GUI-AC: Enhancing Continual Learning in GUI Agents","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2505.17829","title":"Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoning","created":"2025-05-23","cited_by_count":0,"area":"lr"},{"id":"2509.25240","title":"HAMMER: Hamiltonian Curiosity Augmented Large Language Model Reinforcement","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2605.12518","title":"TimelineReasoner: Advancing Timeline Summarization with Large Reasoning Models","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"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":"2607.24617","title":"LaRec: Unleashing LLM-based Latent Reasoning for Generative Recommendation","created":"2026-07-27","cited_by_count":0,"area":"lr"},{"id":"2610.11132","title":"SFT-as-Context Mitigates Forgetting in Supervised Fine-Tuning","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}