{"total":239,"rows":[{"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":"2503.12937","title":"R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization","created":"2025-03-17","cited_by_count":301,"area":"lr"},{"id":"2412.18925","title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","created":"2024-12-25","cited_by_count":265,"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":"2402.06457","title":"V-STaR: Training Verifiers for Self-Taught Reasoners","created":"2024-02-09","cited_by_count":217,"area":"lr"},{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166,"area":"lr"},{"id":"2503.23829","title":"Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains","created":"2025-03-31","cited_by_count":156,"area":"lr"},{"id":"2502.05450","title":"ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy","created":"2025-02-08","cited_by_count":154,"area":"vla"},{"id":"2509.09674","title":"SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning","created":"2025-09-11","cited_by_count":151,"area":"vla"},{"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":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2404.02039","title":"A Survey on Large Language Model-Based Game Agents","created":"2024-04-02","cited_by_count":112,"area":"agents"},{"id":"2503.24047","title":"Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents","created":"2025-03-31","cited_by_count":98,"area":"agents"},{"id":"2406.09136","title":"Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs","created":"2024-06-13","cited_by_count":96,"area":"lr"},{"id":"2505.12434","title":"VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning","created":"2025-05-18","cited_by_count":93,"area":"lr"},{"id":"2505.03318","title":"Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning","created":"2025-05-06","cited_by_count":90,"area":"lr"},{"id":"2406.11176","title":"Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement","created":"2024-06-17","cited_by_count":88,"area":"agents"},{"id":"2505.14231","title":"UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning","created":"2025-05-20","cited_by_count":84,"area":"lr"},{"id":"2503.16252","title":"Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning","created":"2025-03-20","cited_by_count":83,"area":"lr"},{"id":"2504.05185","title":"Concise Reasoning via Reinforcement Learning","created":"2025-04-07","cited_by_count":79,"area":"lr"},{"id":"2509.08755","title":"AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning","created":"2025-09-10","cited_by_count":72,"area":"agents"},{"id":"2409.14924","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","created":"2024-09-23","cited_by_count":66,"area":"rag"},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64,"area":"lr"},{"id":"2505.23646","title":"Are Reasoning Models More Prone to Hallucination?","created":"2025-05-29","cited_by_count":64,"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":"2506.06395","title":"Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models","created":"2025-06-05","cited_by_count":62,"area":"lr"},{"id":"2501.11284","title":"RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?","created":"2025-01-20","cited_by_count":60,"area":"lr"},{"id":"2507.08794","title":"One Token to Fool LLM-as-a-Judge","created":"2025-07-11","cited_by_count":60,"area":"alignment"},{"id":"2403.02333","title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","created":"2024-03-04","cited_by_count":58,"area":"lr"},{"id":"2508.14029","title":"Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR","created":"2025-08-19","cited_by_count":54,"area":"lr"},{"id":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"area":"lr"},{"id":"2505.20272","title":"Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning","created":"2025-05-26","cited_by_count":49,"area":"lr"},{"id":"2505.21318","title":"Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations","created":"2025-05-27","cited_by_count":49,"area":"lr"},{"id":"2407.08733","title":"Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist","created":"2024-07-11","cited_by_count":48,"area":"lr"},{"id":"2507.05386","title":"Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training","created":"2025-07-07","cited_by_count":47,"area":null},{"id":"2510.18927","title":"BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping","created":"2025-10-21","cited_by_count":47,"area":null},{"id":"2503.12434","title":"A Survey on the Optimization of Large Language Model-based Agents","created":"2025-03-16","cited_by_count":46,"area":"agents"},{"id":"2506.01391","title":"AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning","created":"2025-06-02","cited_by_count":44,"area":"agents"},{"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":"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":"2502.12853","title":"S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning","created":"2025-02-18","cited_by_count":39,"area":"lr"},{"id":"2505.20258","title":"ARM: Adaptive Reasoning Model","created":"2025-05-26","cited_by_count":39,"area":"lr"},{"id":"2402.12914","title":"Large Language Model-based Human-Agent Collaboration for Complex Task Solving","created":"2024-02-20","cited_by_count":38,"area":"agents"},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"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":"2502.08127","title":"Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance","created":"2025-02-12","cited_by_count":35,"area":"lr"},{"id":"2502.14565","title":"ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification","created":"2025-02-20","cited_by_count":35,"area":"lr"},{"id":"2502.12970","title":"Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking","created":"2025-02-18","cited_by_count":34,"area":"lr"},{"id":"2505.18237","title":"Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens","created":"2025-05-23","cited_by_count":34,"area":"lr"},{"id":"2501.07861","title":"ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding","created":"2025-01-14","cited_by_count":32,"area":"lr"},{"id":"2503.02875","title":"The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models","created":"2025-03-04","cited_by_count":31,"area":"lr"},{"id":"2406.05673","title":"Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples","created":"2024-06-09","cited_by_count":30,"area":"lr"},{"id":"2502.20127","title":"SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning","created":"2025-02-27","cited_by_count":28,"area":"lr"},{"id":"2503.10814","title":"Thinking Machines: A Survey of LLM based Reasoning Strategies","created":"2025-03-13","cited_by_count":25,"area":"lr"},{"id":"2504.15777","title":"Tina: Tiny Reasoning Models via LoRA","created":"2025-04-22","cited_by_count":25,"area":"lr"},{"id":"2505.13026","title":"Step-wise Adaptive Integration of Supervised Fine-tuning and Reinforcement Learning for Task-Specific LLMs","created":"2025-05-19","cited_by_count":25,"area":"lr"},{"id":"2506.15421","title":"Reward Models in Deep Reinforcement Learning: A Survey","created":"2025-06-18","cited_by_count":25,"area":"alignment"},{"id":"2405.00402","title":"Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models","created":"2024-05-01","cited_by_count":24,"area":"lr"},{"id":"2410.18693","title":"Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch","created":"2024-10-24","cited_by_count":24,"area":"lr"},{"id":"2411.00053","title":"ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration","created":"2024-10-30","cited_by_count":24,"area":"agents"},{"id":"2504.08672","title":"Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning","created":"2025-04-11","cited_by_count":24,"area":"lr"},{"id":"2508.05618","title":"Learning to Reason for Factuality","created":"2025-08-07","cited_by_count":24,"area":"lr"},{"id":"2402.01749","title":"Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models","created":"2024-01-30","cited_by_count":23,"area":null},{"id":"2410.09713","title":"Agentic Information Retrieval","created":"2024-10-13","cited_by_count":21,"area":"agents"},{"id":"2512.16848","title":"Meta-RL Induces Exploration in Language Agents","created":"2025-12-18","cited_by_count":21,"area":"lr"},{"id":"2505.16690","title":"Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator","created":"2025-05-22","cited_by_count":20,"area":null},{"id":"2505.19767","title":"RFTF: Reinforcement Fine-tuning for Embodied Agents with Temporal Feedback","created":"2025-05-26","cited_by_count":20,"area":"vla"},{"id":"2512.21852","title":"A Comedy of Estimators: On KL Regularization in RL Training of LLMs","created":"2025-12-26","cited_by_count":18,"area":"lr"},{"id":"2505.19094","title":"SATORI-R1: Incentivizing Multimodal Reasoning through Explicit Visual Anchoring","created":"2025-05-25","cited_by_count":17,"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":"2505.12366","title":"DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization","created":"2025-05-18","cited_by_count":16,"area":"lr"},{"id":"2505.15710","title":"Advancing LLM Safe Alignment with Safety Representation Ranking","created":"2025-05-21","cited_by_count":16,"area":"safety"},{"id":"2510.06077","title":"When Thinking Drifts: Evidential Grounding for Robust Video Reasoning","created":"2025-10-07","cited_by_count":16,"area":null},{"id":"2405.04086","title":"Optimizing Language Model's Reasoning Abilities with Weak Supervision","created":"2024-05-07","cited_by_count":15,"area":"lr"},{"id":"2507.05197","title":"Pre-Trained Policy Discriminators are General Reward Models","created":"2025-07-07","cited_by_count":15,"area":"alignment"},{"id":"2501.01478","title":"Enhancing Reasoning through Process Supervision with Monte Carlo Tree Search","created":"2025-01-02","cited_by_count":14,"area":"lr"},{"id":"2505.10937","title":"Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations","created":"2025-05-16","cited_by_count":14,"area":"lr"},{"id":"2505.18700","title":"GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains","created":"2025-05-24","cited_by_count":14,"area":"lr"},{"id":"2505.24105","title":"Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning","created":"2025-05-30","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":"2601.06748","title":"On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning","created":"2026-01-11","cited_by_count":14,"area":"vla"},{"id":"2602.11164","title":"Automated Optimization Modeling via a Localizable Error-Driven Perspective","created":"2026-01-17","cited_by_count":14,"area":null},{"id":"2402.12621","title":"Reflect-RL: Two-Player Online RL Fine-Tuning for LMs","created":"2024-02-20","cited_by_count":13,"area":null},{"id":"2410.10370","title":"Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps","created":"2024-10-14","cited_by_count":13,"area":"lr"},{"id":"2412.16849","title":"OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning","created":"2024-12-22","cited_by_count":13,"area":"lr"},{"id":"2509.08621","title":"AdsQA: Towards Advertisement Video Understanding","created":"2025-09-10","cited_by_count":13,"area":null},{"id":"2510.04028","title":"The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View","created":"2025-10-05","cited_by_count":13,"area":"lr"},{"id":"2512.01763","title":"HiconAgent: History Context-aware Policy Optimization for GUI Agents","created":"2025-12-01","cited_by_count":13,"area":"agents"},{"id":"2502.19402","title":"General Intelligence Requires Reward-based Pretraining","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2503.17726","title":"A Survey on Mathematical Reasoning and Optimization with Large Language Models","created":"2025-03-22","cited_by_count":12,"area":"lr"},{"id":"2505.16475","title":"ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection","created":"2025-05-22","cited_by_count":12,"area":null},{"id":"2505.17767","title":"Position: The Real Barrier to LLM Agent Usability is Agentic ROI","created":"2025-05-23","cited_by_count":12,"area":"agents"},{"id":"2507.03483","title":"BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset","created":"2025-07-04","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":"2402.15729","title":"How Do Humans Write Code? Large Models Do It the Same Way Too","created":"2024-02-24","cited_by_count":11,"area":"lr"},{"id":"2412.15305","title":"Tree-of-Code: A Tree-Structured Exploring Framework for End-to-End Code Generation and Execution in Complex Task Handling","created":"2024-12-19","cited_by_count":11,"area":"lr"},{"id":"2601.18984","title":"Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning","created":"2026-01-26","cited_by_count":11,"area":"lr"},{"id":"2602.07605","title":"Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning","created":"2026-02-07","cited_by_count":11,"area":"lr"},{"id":"2502.04667","title":"Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning","created":"2025-02-07","cited_by_count":10,"area":"lr"},{"id":"2502.17720","title":"Spontaneous Giving and Calculated Greed in Language Models","created":"2025-02-24","cited_by_count":10,"area":"lr"}],"next_cursor":"100"}