{"total":196,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820,"area":"lr"},{"id":"2502.09601","title":"CoT-Valve: Length-Compressible Chain-of-Thought Tuning","created":"2025-02-13","cited_by_count":169,"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":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133,"area":"lr"},{"id":"2504.07912","title":"Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining","created":"2025-04-10","cited_by_count":129,"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":"2510.14901","title":"Reasoning with Sampling: Your Base Model is Smarter Than You Think","created":"2025-10-16","cited_by_count":89,"area":"lr"},{"id":"2503.10497","title":"MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation","created":"2025-03-13","cited_by_count":79,"area":"lr"},{"id":"2502.08606","title":"Distillation Scaling Laws","created":"2025-02-12","cited_by_count":67,"area":"lr"},{"id":"2506.17211","title":"BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning","created":"2025-06-20","cited_by_count":63,"area":"lr"},{"id":"2505.08054","title":"FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning","created":"2025-05-12","cited_by_count":58,"area":"lr"},{"id":"2506.17238","title":"Training a Scientific Reasoning Model for Chemistry","created":"2025-06-04","cited_by_count":56,"area":"lr"},{"id":"2505.12864","title":"LEXam: Benchmarking Legal Reasoning on 340 Law Exams","created":"2025-05-19","cited_by_count":54,"area":"lr"},{"id":"2502.02508","title":"Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search","created":"2025-02-04","cited_by_count":53,"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":"2508.02095","title":"VLM4D: Towards Spatiotemporal Awareness in Vision Language Models","created":"2025-08-04","cited_by_count":46,"area":"lr"},{"id":"2503.18866","title":"Reasoning to Learn from Latent Thoughts","created":"2025-03-24","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":"2510.25760","title":"Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks","created":"2025-10-29","cited_by_count":33,"area":"lr"},{"id":"2507.11407","title":"EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes","created":"2025-07-15","cited_by_count":32,"area":"lr"},{"id":"2507.23751","title":"CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks","created":"2025-07-31","cited_by_count":32,"area":"lr"},{"id":"2510.20733","title":"Thought Communication in Multiagent Collaboration","created":"2025-10-23","cited_by_count":30,"area":"lr"},{"id":"2505.24863","title":"AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time","created":"2025-05-30","cited_by_count":29,"area":"lr"},{"id":"2412.17596","title":"Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Context","created":"2024-12-23","cited_by_count":28,"area":"lr"},{"id":"2510.01624","title":"Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead","created":"2025-10-02","cited_by_count":28,"area":"lr"},{"id":"2510.01499","title":"Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information","created":"2025-10-01","cited_by_count":26,"area":"lr"},{"id":"2512.12895","title":"Wait, Wait, Wait... Why Do Reasoning Models Loop?","created":"2025-12-15","cited_by_count":26,"area":"lr"},{"id":"2509.26062","title":"DyFlow: Dynamic Workflow Framework for Agentic Reasoning","created":"2025-09-30","cited_by_count":23,"area":"lr"},{"id":"2502.06773","title":"On the Emergence of Thinking in LLMs I: Searching for the Right Intuition","created":"2025-02-10","cited_by_count":22,"area":"lr"},{"id":"2511.11025","title":"AirCopBench: A Benchmark for Multi-drone Collaborative Embodied Perception and Reasoning","created":"2025-11-14","cited_by_count":20,"area":"lr"},{"id":"2501.09213","title":"FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training","created":"2025-01-16","cited_by_count":19,"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":"2505.24876","title":"Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks","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":"2504.14350","title":"An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint","created":"2025-04-19","cited_by_count":17,"area":"lr"},{"id":"2508.14094","title":"Hard Examples Are All You Need: Maximizing GRPO Post-Training Under Annotation Budgets","created":"2025-08-15","cited_by_count":17,"area":"lr"},{"id":"2502.12470","title":"Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinking","created":"2025-02-18","cited_by_count":16,"area":"lr"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2503.10009","title":"OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLM","created":"2025-03-13","cited_by_count":15,"area":"lr"},{"id":"2502.13389","title":"Reasoning with Reinforced Functional Token Tuning","created":"2025-02-19","cited_by_count":14,"area":"lr"},{"id":"2508.14313","title":"AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning","created":"2025-08-19","cited_by_count":14,"area":"lr"},{"id":"2502.04375","title":"An Analysis for Reasoning Bias of Language Models with Small Initialization","created":"2025-02-05","cited_by_count":13,"area":"lr"},{"id":"2504.11919","title":"Rethinking the Generation of High-Quality CoT Data from the Perspective of LLM-Adaptive Question Difficulty Grading","created":"2025-04-16","cited_by_count":11,"area":"lr"},{"id":"2505.23713","title":"SocialMaze: A Benchmark for Evaluating and Enhancing Social Reasoning in Large Language Models in Complex Social Environments","created":"2025-05-29","cited_by_count":11,"area":"lr"},{"id":"2508.21422","title":"Automatic Reviewers Fail to Detect Faulty Reasoning in Research Papers: A New Counterfactual Evaluation Framework","created":"2025-08-29","cited_by_count":11,"area":"lr"},{"id":"2510.06036","title":"Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?","created":"2025-10-07","cited_by_count":11,"area":"lr"},{"id":"2512.17319","title":"A Benchmark for Ultra-High-Resolution Remote Sensing MLLMs","created":"2025-12-19","cited_by_count":11,"area":"lr"},{"id":"2501.03265","title":"Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deployment","created":"2025-01-04","cited_by_count":10,"area":"lr"},{"id":"2504.00043","title":"CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation","created":"2025-03-30","cited_by_count":10,"area":"lr"},{"id":"2505.24173","title":"DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?","created":"2025-05-30","cited_by_count":10,"area":"lr"},{"id":"2509.23392","title":"Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking","created":"2025-09-27","cited_by_count":10,"area":"lr"},{"id":"2509.24156","title":"Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2510.24081","title":"Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures","created":"2025-10-28","cited_by_count":10,"area":"lr"},{"id":"2511.23478","title":"Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models","created":"2025-11-28","cited_by_count":10,"area":"lr"},{"id":"2509.19894","title":"PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning","created":"2025-09-24","cited_by_count":9,"area":"lr"},{"id":"2502.05449","title":"Iterative Deepening Sampling as Efficient Test-Time Scaling","created":"2025-02-08","cited_by_count":8,"area":"lr"},{"id":"2506.06972","title":"Atomic Reasoning for Scientific Table Claim Verification","created":"2025-06-08","cited_by_count":8,"area":"lr"},{"id":"2512.19995","title":"Schoenfeld's Anatomy of Mathematical Reasoning by Language Models","created":"2025-12-23","cited_by_count":8,"area":"lr"},{"id":"2603.03205","title":"Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use","created":"2026-03-03","cited_by_count":8,"area":"lr"},{"id":"2501.11790","title":"Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions","created":"2025-01-20","cited_by_count":7,"area":"lr"},{"id":"2504.15415","title":"IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs","created":"2025-04-21","cited_by_count":7,"area":"lr"},{"id":"2505.17315","title":"Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2508.00079","title":"PhysicsEval: Inference-Time Techniques to Improve the Reasoning Proficiency of Large Language Models on Physics Problems","created":"2025-07-31","cited_by_count":7,"area":"lr"},{"id":"2510.15987","title":"AlgoTrace: Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2601.21051","title":"Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Report","created":"2026-01-28","cited_by_count":7,"area":"lr"},{"id":"2606.01476","title":"OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification","created":"2026-05-31","cited_by_count":7,"area":"lr"},{"id":"2502.19058","title":"MathDebugger: Detecting and Diagnosing Errors in Synthetic Mathematical Data","created":"2025-02-26","cited_by_count":6,"area":"lr"},{"id":"2505.11031","title":"OntoURL: A Benchmark for Evaluating Large Language Models on Symbolic Ontological Understanding, Reasoning and Learning","created":"2025-05-16","cited_by_count":6,"area":"lr"},{"id":"2505.15734","title":"DEBATE, TRAIN, EVOLVE: Self Evolution of Language Model Reasoning","created":"2025-05-21","cited_by_count":6,"area":"lr"},{"id":"2507.00951","title":"Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact","created":"2025-07-01","cited_by_count":6,"area":"lr"},{"id":"2509.00544","title":"When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced Misalignment","created":"2025-08-30","cited_by_count":6,"area":"lr"},{"id":"2511.00640","title":"DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching","created":"2025-11-01","cited_by_count":6,"area":"lr"},{"id":"2601.06767","title":"GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2602.24014","title":"Interpretable Debiasing of Vision-Language Models for Social Fairness","created":"2026-02-27","cited_by_count":6,"area":"lr"},{"id":"2605.25864","title":"When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards","created":"2026-05-25","cited_by_count":6,"area":"lr"},{"id":"2606.03458","title":"KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks","created":"2026-06-02","cited_by_count":6,"area":"lr"},{"id":"2501.02795","title":"InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusion","created":"2025-01-06","cited_by_count":5,"area":"lr"},{"id":"2501.13620","title":"A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs","created":"2025-01-23","cited_by_count":5,"area":"lr"},{"id":"2504.05632","title":"Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning","created":"2025-04-08","cited_by_count":5,"area":"lr"},{"id":"2507.05934","title":"BlueLM-2.5-3B Technical Report","created":"2025-07-08","cited_by_count":5,"area":"lr"},{"id":"2507.18178","title":"Decoupling Knowledge and Reasoning in LLMs: An Exploration Using Cognitive Dual-System Theory","created":"2025-07-24","cited_by_count":5,"area":"lr"},{"id":"2511.16940","title":"MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models","created":"2025-11-21","cited_by_count":5,"area":"lr"},{"id":"2511.19972","title":"Boosting Reasoning in Large Multimodal Models via Activation Replay","created":"2025-11-25","cited_by_count":5,"area":"lr"},{"id":"2502.15854","title":"Enhancing Domain-Specific Retrieval-Augmented Generation: Synthetic Data Generation and Evaluation using Reasoning Models","created":"2025-02-21","cited_by_count":4,"area":"lr"},{"id":"2503.04813","title":"Self-Evolved Preference Optimization for Enhancing Mathematical Reasoning in Small Language Models","created":"2025-03-04","cited_by_count":4,"area":"lr"},{"id":"2503.05891","title":"MastermindEval: A Simple But Scalable Reasoning Benchmark","created":"2025-03-07","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":"2510.07731","title":"oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning","created":"2025-10-09","cited_by_count":4,"area":"lr"},{"id":"2510.25804","title":"Beyond Length: Quantifying Long-Range Information for Long-Context LLM Pretraining Data","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2511.12263","title":"CrossVid: A Comprehensive Benchmark for Evaluating Cross-Video Reasoning in Multimodal Large Language Models","created":"2025-11-15","cited_by_count":4,"area":"lr"},{"id":"2602.09782","title":"Flexible Entropy Control in RLVR with a Gradient-Preserving Perspective","created":"2026-02-10","cited_by_count":4,"area":"lr"},{"id":"2602.14868","title":"Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning","created":"2026-02-16","cited_by_count":4,"area":"lr"},{"id":"2602.19548","title":"Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining","created":"2026-02-23","cited_by_count":4,"area":"lr"},{"id":"2502.02007","title":"Reasoning Bias of Next Token Prediction Training","created":"2025-02-04","cited_by_count":3,"area":"lr"},{"id":"2503.23487","title":"Large Language and Reasoning Models are Shallow Disjunctive Reasoners","created":"2025-03-30","cited_by_count":3,"area":"lr"},{"id":"2505.23982","title":"MSQA: Benchmarking LLMs on Graduate-Level Materials Science Reasoning and Knowledge","created":"2025-05-29","cited_by_count":3,"area":"lr"},{"id":"2510.09351","title":"ReTraceQA: Evaluating Reasoning Traces of Small Language Models in Commonsense Question Answering","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2510.15040","title":"Composition-Grounded Data Synthesis for Visual Reasoning","created":"2025-10-16","cited_by_count":3,"area":"lr"},{"id":"2510.23486","title":"Learning to Reason Efficiently with Discounted Reinforcement Learning","created":"2025-10-27","cited_by_count":3,"area":"lr"}],"next_cursor":"100"}