{"total":67,"rows":[{"id":"2508.06471","title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","created":"2025-08-08","cited_by_count":467,"area":"lr"},{"id":"2502.18449","title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","created":"2025-02-25","cited_by_count":263,"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":"2412.18194","title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks","created":"2024-12-24","cited_by_count":175,"area":"lr"},{"id":"2406.17294","title":"Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models","created":"2024-06-25","cited_by_count":133,"area":"lr"},{"id":"2506.20512","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","created":"2025-06-25","cited_by_count":113,"area":"lr"},{"id":"2508.14444","title":"NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model","created":"2025-08-20","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":"2508.11408","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","created":"2025-08-15","cited_by_count":91,"area":"lr"},{"id":"2502.08606","title":"Distillation Scaling Laws","created":"2025-02-12","cited_by_count":67,"area":"lr"},{"id":"2412.16145","title":"Offline Reinforcement Learning for LLM Multi-Step Reasoning","created":"2024-12-20","cited_by_count":54,"area":"lr"},{"id":"2504.02807","title":"MegaMath: Pushing the Limits of Open Math Corpora","created":"2025-04-03","cited_by_count":51,"area":"lr"},{"id":"2405.14365","title":"JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models","created":"2024-05-23","cited_by_count":45,"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":"2405.06001","title":"LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit","created":"2024-05-09","cited_by_count":33,"area":"lr"},{"id":"2505.07538","title":"Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning","created":"2025-05-12","cited_by_count":33,"area":"lr"},{"id":"2505.10475","title":"Parallel Scaling Law for Language Models","created":"2025-05-15","cited_by_count":30,"area":"lr"},{"id":"2505.24714","title":"FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation","created":"2025-05-30","cited_by_count":30,"area":"lr"},{"id":"2502.18878","title":"Learning to Generate Structured Output with Schema Reinforcement Learning","created":"2025-02-26","cited_by_count":29,"area":"lr"},{"id":"2502.20339","title":"Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners","created":"2025-02-27","cited_by_count":22,"area":"lr"},{"id":"2503.18071","title":"Mind with Eyes: from Language Reasoning to Multimodal Reasoning","created":"2025-03-23","cited_by_count":22,"area":"lr"},{"id":"2603.12262","title":"Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously","created":"2026-03-12","cited_by_count":22,"area":"lr"},{"id":"2510.23569","title":"EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT","created":"2025-10-27","cited_by_count":16,"area":"lr"},{"id":"2406.11288","title":"MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Models","created":"2024-06-17","cited_by_count":15,"area":"lr"},{"id":"2510.12184","title":"CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs","created":"2025-10-14","cited_by_count":14,"area":"lr"},{"id":"2512.02624","title":"PPTBench: Towards Holistic Evaluation of Large Language Models for PowerPoint Layout and Design Understanding","created":"2025-12-02","cited_by_count":14,"area":"lr"},{"id":"2602.05547","title":"Multi-Task GRPO: Reliable LLM Reasoning Across Tasks","created":"2026-02-05","cited_by_count":14,"area":"lr"},{"id":"2409.13730","title":"VisScience: An Extensive Benchmark for Evaluating K12 Educational Multi-modal Scientific Reasoning","created":"2024-09-10","cited_by_count":13,"area":"lr"},{"id":"2501.14002","title":"Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages","created":"2025-01-23","cited_by_count":13,"area":"lr"},{"id":"2410.16670","title":"CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing","created":"2024-10-22","cited_by_count":12,"area":"lr"},{"id":"2508.16859","title":"Beyond Emotion Recognition: A Multi-Turn Multimodal Emotion Understanding and Reasoning Benchmark","created":"2025-08-23","cited_by_count":12,"area":"lr"},{"id":"2507.06607","title":"Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation","created":"2025-07-09","cited_by_count":11,"area":"lr"},{"id":"2509.23324","title":"Scaling LLM Test-Time Compute with Mobile NPU on Smartphones","created":"2025-09-27","cited_by_count":11,"area":"lr"},{"id":"2410.02229","title":"CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning","created":"2024-10-03","cited_by_count":10,"area":"lr"},{"id":"2509.04744","title":"WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning","created":"2025-09-05","cited_by_count":10,"area":"lr"},{"id":"2505.24550","title":"A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings","created":"2025-05-30","cited_by_count":9,"area":"lr"},{"id":"2512.08580","title":"Mind to Hand: Purposeful Robotic Control via Embodied Reasoning","created":"2025-12-09","cited_by_count":8,"area":"lr"},{"id":"2505.23242","title":"ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering","created":"2025-05-29","cited_by_count":7,"area":"lr"},{"id":"2506.22403","title":"HyperCLOVA X THINK Technical Report","created":"2025-06-27","cited_by_count":7,"area":"lr"},{"id":"2410.09407","title":"CAMPHOR: Collaborative Agents for Multi-input Planning and High-Order Reasoning On Device","created":"2024-10-12","cited_by_count":6,"area":"lr"},{"id":"2502.17888","title":"RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts","created":"2025-02-25","cited_by_count":6,"area":"lr"},{"id":"2512.18196","title":"LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision","created":"2025-12-20","cited_by_count":6,"area":"lr"},{"id":"2503.16856","title":"MMCR: Benchmarking Cross-Source Reasoning in Scientific Papers","created":"2025-03-21","cited_by_count":5,"area":"lr"},{"id":"2505.07293","title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection","created":"2025-05-12","cited_by_count":5,"area":"lr"},{"id":"2505.13419","title":"FEALLM: Advancing Facial Emotion Analysis in Multimodal Large Language Models with Emotional Synergy and Reasoning","created":"2025-05-19","cited_by_count":5,"area":"lr"},{"id":"2505.21962","title":"A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding","created":"2025-05-28","cited_by_count":5,"area":"lr"},{"id":"2602.00642","title":"LegalOne: A Family of Foundation Models for Reliable Legal Reasoning","created":"2026-01-31","cited_by_count":5,"area":"lr"},{"id":"2507.02804","title":"Multimodal Mathematical Reasoning with Diverse Solving Perspective","created":"2025-07-03","cited_by_count":4,"area":"lr"},{"id":"2508.07630","title":"InterChart: Benchmarking Visual Reasoning Across Decomposed and Distributed Chart Information","created":"2025-08-11","cited_by_count":4,"area":"lr"},{"id":"2512.24503","title":"Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice","created":"2025-12-30","cited_by_count":3,"area":"lr"},{"id":"2604.15701","title":"Improving Reasoning Capabilities in Small Models through Mixture-of-Layers Distillation with Stepwise Attention on Key Information","created":"2026-04-17","cited_by_count":3,"area":"lr"},{"id":"2511.17487","title":"Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models","created":"2025-11-21","cited_by_count":2,"area":"lr"},{"id":"2603.02099","title":"Recursive Think-Answer Process for LLMs and VLMs","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2604.10228","title":"SVSR: A Self-Verification and Self-Rectification Paradigm for Multimodal Reasoning","created":"2026-04-11","cited_by_count":2,"area":"lr"},{"id":"2605.29327","title":"Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2502.08903","title":"3D-Grounded Vision-Language Framework for Robotic Task Planning: Automated Prompt Synthesis and Supervised Reasoning","created":"2025-02-13","cited_by_count":1,"area":"lr"},{"id":"2509.10059","title":"Multimodal Mathematical Reasoning Embedded in Aerial Vehicle Imagery: Benchmarking, Analysis, and Exploration","created":"2025-09-12","cited_by_count":1,"area":"lr"},{"id":"2602.19505","title":"Test-Time Computing for Referring Multimodal Large Language Models","created":"2026-02-23","cited_by_count":1,"area":"lr"},{"id":"2412.19638","title":"Xmodel-2 Technical Report","created":"2024-12-27","cited_by_count":0,"area":"lr"},{"id":"2510.01528","title":"Towards Interpretable and Inference-Optimal COT Reasoning with Sparse Autoencoder-Guided Generation","created":"2025-10-02","cited_by_count":0,"area":"lr"},{"id":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2607.05089","title":"TimeThink: Reasoning with Time for Video LLMs","created":"2026-07-06","cited_by_count":0,"area":"lr"},{"id":"2609.16557","title":"PunGraph: Retrieval-Enhanced Phonetic-Semantic Graph Reasoning for Pun Understanding","created":"2026-09-15","cited_by_count":0,"area":"lr"},{"id":"2609.31947","title":"On-Policy Attention Linearization","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.37169","title":"Trajectory Soup: Pushing the Compute-Scaling Frontier of LLM Mid-training via Diverse Trajectories","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.08830","title":"MoR-MLLM: Mixture of Recursions for Efficient Multimodal Large Language Models","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2610.19871","title":"Rationale Distribution Distillation via Flow Matching for Distributional Continuous Latent Reasoning","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}