{"total":112,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132,"area":"lr"},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345,"area":"lr"},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210,"area":"lr"},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642,"area":"lr"},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596,"area":"lr"},{"id":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388,"area":"lr"},{"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":"2505.24298","title":"AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning","created":"2025-05-30","cited_by_count":250,"area":"lr"},{"id":"2507.02592","title":"WebSailor: Navigating Super-human Reasoning for Web Agent","created":"2025-07-03","cited_by_count":229,"area":"lr"},{"id":"2506.23918","title":"Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers","created":"2025-06-30","cited_by_count":199,"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":"2503.15558","title":"Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning","created":"2025-03-18","cited_by_count":164,"area":"lr"},{"id":"2505.00949","title":"Llama-Nemotron: Efficient Reasoning Models","created":"2025-05-02","cited_by_count":158,"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":"2505.13379","title":"Thinkless: LLM Learns When to Think","created":"2025-05-19","cited_by_count":113,"area":"lr"},{"id":"2508.11737","title":"Ovis2.5 Technical Report","created":"2025-08-15","cited_by_count":108,"area":"lr"},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104,"area":"lr"},{"id":"2506.06122","title":"Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library","created":"2025-06-06","cited_by_count":101,"area":"lr"},{"id":"2504.03624","title":"Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models","created":"2025-04-04","cited_by_count":100,"area":"lr"},{"id":"2405.10825","title":"Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities","created":"2024-05-17","cited_by_count":83,"area":"lr"},{"id":"2509.13305","title":"WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning","created":"2025-09-16","cited_by_count":61,"area":"lr"},{"id":"2509.15965","title":"RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation","created":"2025-09-19","cited_by_count":57,"area":"lr"},{"id":"2510.18855","title":"Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model","created":"2025-10-21","cited_by_count":55,"area":"lr"},{"id":"2512.23703","title":"Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation","created":"2025-12-29","cited_by_count":40,"area":"lr"},{"id":"2508.15096","title":"Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset","created":"2025-08-20","cited_by_count":38,"area":"lr"},{"id":"2509.21009","title":"RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training","created":"2025-09-25","cited_by_count":35,"area":"lr"},{"id":"2505.10475","title":"Parallel Scaling Law for Language Models","created":"2025-05-15","cited_by_count":30,"area":"lr"},{"id":"2509.18521","title":"APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation","created":"2025-09-23","cited_by_count":30,"area":"lr"},{"id":"2308.08784","title":"CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation","created":"2023-08-17","cited_by_count":29,"area":"lr"},{"id":"2505.08311","title":"AM-Thinking-v1: Advancing the Frontier of Reasoning at 32B Scale","created":"2025-05-13","cited_by_count":29,"area":"lr"},{"id":"2512.21919","title":"SWE-RM: Execution-free Feedback For Software Engineering Agents","created":"2025-12-26","cited_by_count":28,"area":"lr"},{"id":"2510.01265","title":"RLP: Reinforcement as a Pretraining Objective","created":"2025-09-26","cited_by_count":25,"area":"lr"},{"id":"2509.18883","title":"Introducing LongCat-Flash-Thinking: A Technical Report","created":"2025-09-23","cited_by_count":22,"area":"lr"},{"id":"2505.02881","title":"Rewriting Pre-Training Data Boosts LLM Performance in Math and Code","created":"2025-05-05","cited_by_count":21,"area":"lr"},{"id":"2503.17604","title":"OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery","created":"2025-03-22","cited_by_count":20,"area":"lr"},{"id":"2212.08286","title":"ALERT: Adapting Language Models to Reasoning Tasks","created":"2022-12-16","cited_by_count":17,"area":"lr"},{"id":"2409.11538","title":"Chain-of-Thought Prompting for Speech Translation","created":"2024-09-17","cited_by_count":17,"area":"lr"},{"id":"2510.15414","title":"MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs","created":"2025-10-17","cited_by_count":16,"area":"lr"},{"id":"2304.13911","title":"Federated Prompting and Chain-of-Thought Reasoning for Improving LLMs Answering","created":"2023-04-27","cited_by_count":14,"area":"lr"},{"id":"2410.12881","title":"MIND: Math Informed syNthetic Dialogues for Pretraining LLMs","created":"2024-10-15","cited_by_count":14,"area":"lr"},{"id":"2504.06214","title":"From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models","created":"2025-04-08","cited_by_count":14,"area":"lr"},{"id":"2403.07872","title":"Rethinking Generative Large Language Model Evaluation for Semantic Comprehension","created":"2024-03-12","cited_by_count":13,"area":"lr"},{"id":"2406.12442","title":"Abstraction-of-Thought Makes Language Models Better Reasoners","created":"2024-06-18","cited_by_count":11,"area":"lr"},{"id":"2510.19225","title":"RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs","created":"2025-10-22","cited_by_count":11,"area":"lr"},{"id":"2601.14243","title":"Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow","created":"2026-01-20","cited_by_count":11,"area":"lr"},{"id":"2605.10325","title":"Verifiable Process Rewards for Agentic Reasoning","created":"2026-05-11","cited_by_count":11,"area":"lr"},{"id":"2605.07177","title":"HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents","created":"2026-05-08","cited_by_count":10,"area":"lr"},{"id":"2509.11961","title":"Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding","created":"2025-09-15","cited_by_count":9,"area":"lr"},{"id":"2511.13612","title":"P1: Mastering Physics Olympiads with Reinforcement Learning","created":"2025-11-17","cited_by_count":8,"area":"lr"},{"id":"2503.09620","title":"Exploiting Edited Large Language Models as General Scientific Optimizers","created":"2025-03-08","cited_by_count":7,"area":"lr"},{"id":"2508.21365","title":"Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models","created":"2025-08-29","cited_by_count":7,"area":"lr"},{"id":"2601.22718","title":"A Step Back: Prefix Importance Ratio Stabilizes Policy Optimization","created":"2026-01-30","cited_by_count":7,"area":"lr"},{"id":"2602.09443","title":"P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2604.11554","title":"Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale","created":"2026-04-13","cited_by_count":7,"area":"lr"},{"id":"2605.17570","title":"How Off-Policy Can GRPO Be? Mu-GRPO for Efficient LLM Reinforcement Learning","created":"2026-05-17","cited_by_count":7,"area":"lr"},{"id":"2609.11042","title":"T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks","created":"2026-09-10","cited_by_count":7,"area":"lr"},{"id":"2506.10481","title":"OIBench: Benchmarking Strong Reasoning Models with Olympiad in Informatics","created":"2025-06-12","cited_by_count":6,"area":"lr"},{"id":"2606.09348","title":"PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment","created":"2026-06-08","cited_by_count":6,"area":"lr"},{"id":"2606.18967","title":"EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts","created":"2026-06-17","cited_by_count":6,"area":"lr"},{"id":"2507.05934","title":"BlueLM-2.5-3B Technical Report","created":"2025-07-08","cited_by_count":5,"area":"lr"},{"id":"2601.09083","title":"SRT: Accelerating Reinforcement Learning via Speculative Rollout with Tree-Structured Cache","created":"2026-01-14","cited_by_count":5,"area":"lr"},{"id":"2606.09821","title":"Rethinking the Divergence Regularization in LLM RL","created":"2026-06-08","cited_by_count":5,"area":"lr"},{"id":"2606.19257","title":"DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models","created":"2026-06-17","cited_by_count":5,"area":"lr"},{"id":"2310.06003","title":"Rethinking Memory and Communication Cost for Efficient Large Language Model Training","created":"2023-10-09","cited_by_count":4,"area":"lr"},{"id":"2602.13407","title":"On-Policy Supervised Fine-Tuning for Efficient Reasoning","created":"2026-02-13","cited_by_count":4,"area":"lr"},{"id":"2607.07836","title":"Infinity-Parser2 Technical Report","created":"2026-07-08","cited_by_count":4,"area":"lr"},{"id":"2608.17393","title":"LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents","created":"2026-08-18","cited_by_count":4,"area":"lr"},{"id":"2210.07519","title":"Can Language Representation Models Think in Bets?","created":"2022-10-14","cited_by_count":3,"area":"lr"},{"id":"2505.16928","title":"Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context Reasoning","created":"2025-05-22","cited_by_count":3,"area":"lr"},{"id":"2507.01327","title":"Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy","created":"2025-07-02","cited_by_count":3,"area":"lr"},{"id":"2509.04791","title":"What-If Analysis of Large Language Models: Explore the Game World Using Proactive Thinking","created":"2025-09-05","cited_by_count":3,"area":"lr"},{"id":"2509.25531","title":"MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources","created":"2025-09-29","cited_by_count":3,"area":"lr"},{"id":"2512.06201","title":"K2-V2: A 360-Open, Reasoning-Enhanced LLM","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2602.01103","title":"Probing RLVR training instability through the lens of objective-level hacking","created":"2026-02-01","cited_by_count":3,"area":"lr"},{"id":"2609.07108","title":"Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training","created":"2026-09-07","cited_by_count":3,"area":"lr"},{"id":"2602.08693","title":"Reasoning aligns language models to human cognition","created":"2026-02-09","cited_by_count":2,"area":"lr"},{"id":"2605.06850","title":"How to Compress KV Cache in RL Post-Training? Shadow Mask Distillation for Memory-Efficient Alignment","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2605.28184","title":"Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2510.18672","title":"Reasoning Language Model Inference Serving Unveiled: An Empirical Study","created":"2025-10-21","cited_by_count":1,"area":"lr"},{"id":"2511.18871","title":"Periodic Asynchrony: An On-Policy Approach for Accelerating LLM Reinforcement Learning","created":"2025-11-24","cited_by_count":1,"area":"lr"},{"id":"2602.01563","title":"AdNanny: One Reasoning LLM for All Offline Ads Recommendation Tasks","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2602.08030","title":"Free(): Learning to Forget in Malloc-Only Reasoning Models","created":"2026-02-08","cited_by_count":1,"area":"lr"},{"id":"2602.11081","title":"SteuerLLM: Local specialized large language model for German tax law analysis","created":"2026-02-11","cited_by_count":1,"area":"lr"},{"id":"2602.11937","title":"Extending Puzzle for Mixture-of-Experts Reasoning Models with Application to GPT-OSS Acceleration","created":"2026-02-12","cited_by_count":1,"area":"lr"},{"id":"2604.18187","title":"Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2606.18831","title":"Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning","created":"2026-06-17","cited_by_count":1,"area":"lr"},{"id":"2607.20833","title":"REFACT: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning","created":"2026-07-23","cited_by_count":1,"area":"lr"},{"id":"2607.27919","title":"Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2607.28595","title":"Beacon: Knowing When and How to Perform Agentic Visual Reasoning","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2608.00181","title":"Cross-Benchmark Generalization in Long-Horizon Agents","created":"2026-07-31","cited_by_count":1,"area":"lr"},{"id":"2610.11959","title":"MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement","created":"2026-10-08","cited_by_count":1,"area":"lr"},{"id":"2507.23170","title":"BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM Services with Authenticity and Reasoning","created":"2025-07-31","cited_by_count":0,"area":"lr"},{"id":"2508.08909","title":"Compass-Thinker-7B Technical Report","created":"2025-08-12","cited_by_count":0,"area":"lr"},{"id":"2509.00309","title":"Balanced Actor Initialization: Stable RLHF Training of Distillation-Based Reasoning Models","created":"2025-08-30","cited_by_count":0,"area":"lr"},{"id":"2511.09025","title":"FLAD: Federated Learning for LLM-based Autonomous Driving in Vehicle-Edge-Cloud Networks","created":"2025-11-12","cited_by_count":0,"area":"lr"},{"id":"2512.08944","title":"Enhancing Reliability across Short and Long-Form QA via Reinforcement Learning","created":"2025-11-19","cited_by_count":0,"area":"lr"},{"id":"2602.00748","title":"HyperOffload: Graph-Driven Hierarchical Memory Management for Large Language Models on SuperNode Architectures","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"id":"2603.10492","title":"Human-AI Co-reasoning for Clinical Diagnosis with Evidence-Integrated Language Agent","created":"2026-03-11","cited_by_count":0,"area":"lr"},{"id":"2604.11627","title":"POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2605.09343","title":"SKG-VLA: Scene Knowledge Graph Priors for Structured Scene Semantics and Multimodal Reasoning for Decision Making","created":"2026-05-10","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}