{"list":"other","total":69,"rows":[{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2503.09516","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","created":"2025-03-12","cited_by_count":1444},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2412.16720","title":"OpenAI o1 System Card","created":"2024-12-21","cited_by_count":1244},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"2503.06749","title":"Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models","created":"2025-03-09","cited_by_count":665},{"id":"2504.07615","title":"VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model","created":"2025-04-10","cited_by_count":526},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2503.10615","title":"R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization","created":"2025-03-13","cited_by_count":370},{"id":"2504.13958","title":"ToolRL: Reward is All Tool Learning Needs","created":"2025-04-16","cited_by_count":362},{"id":"2503.05592","title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","created":"2025-03-07","cited_by_count":336},{"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},{"id":"2502.18600","title":"Chain of Draft: Thinking Faster by Writing Less","created":"2025-02-25","cited_by_count":297},{"id":"2501.09686","title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","created":"2025-01-16","cited_by_count":293},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238},{"id":"2503.10460","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond","created":"2025-03-13","cited_by_count":175},{"id":"2309.15789","title":"Large Language Model Routing with Benchmark Datasets","created":"2023-09-27","cited_by_count":172},{"id":"2410.03834","title":"GraphRouter: A Graph-based Router for LLM Selections","created":"2024-10-04","cited_by_count":165},{"id":"2311.08692","title":"Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models","created":"2023-11-15","cited_by_count":145},{"id":"2410.02506","title":"Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems","created":"2024-10-03","cited_by_count":141},{"id":"2408.06195","title":"Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers","created":"2024-08-12","cited_by_count":138},{"id":"2503.05179","title":"Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching","created":"2025-03-07","cited_by_count":117},{"id":"2502.12893","title":"H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking","created":"2025-02-18","cited_by_count":99},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90},{"id":"2502.11133","title":"MasRouter: Learning to Route LLMs for Multi-Agent Systems","created":"2025-02-16","cited_by_count":88},{"id":"2505.07686","title":"S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models","created":"2025-05-12","cited_by_count":87},{"id":"2505.14677","title":"Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning","created":"2025-05-20","cited_by_count":87},{"id":"2502.18036","title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","created":"2025-02-25","cited_by_count":86},{"id":"2506.09033","title":"Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning","created":"2025-06-10","cited_by_count":72},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64},{"id":"2407.06057","title":"Variational Best-of-N Alignment","created":"2024-07-08","cited_by_count":51},{"id":"2502.13260","title":"Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models","created":"2025-02-18","cited_by_count":51},{"id":"2410.02223","title":"EmbedLLM: Learning Compact Representations of Large Language Models","created":"2024-10-03","cited_by_count":48},{"id":"2506.01048","title":"IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory","created":"2025-06-01","cited_by_count":40},{"id":"2506.02536","title":"Answer Convergence as a Signal for Early Stopping in Reasoning","created":"2025-06-03","cited_by_count":40},{"id":"2505.20258","title":"ARM: Adaptive Reasoning Model","created":"2025-05-26","cited_by_count":39},{"id":"2504.03234","title":"Think When You Need: Self-Adaptive Chain-of-Thought Learning","created":"2025-04-04","cited_by_count":38},{"id":"2503.11314","title":"Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering","created":"2025-03-14","cited_by_count":36},{"id":"2505.11277","title":"Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning","created":"2025-05-16","cited_by_count":35},{"id":"2505.12886","title":"Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective","created":"2025-05-19","cited_by_count":34},{"id":"2504.21659","title":"Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization","created":"2025-04-30","cited_by_count":33},{"id":"2502.02421","title":"Activation-Informed Merging of Large Language Models","created":"2025-02-04","cited_by_count":30},{"id":"2505.13975","title":"DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models","created":"2025-05-20","cited_by_count":30},{"id":"2504.08813","title":"SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models","created":"2025-04-09","cited_by_count":29},{"id":"2506.02951","title":"Adaptive Graph Pruning for Multi-Agent Communication","created":"2025-06-03","cited_by_count":29},{"id":"2506.04034","title":"Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning","created":"2025-06-04","cited_by_count":26},{"id":"2502.12202","title":"To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models","created":"2025-02-16","cited_by_count":22},{"id":"2505.11225","title":"HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization","created":"2025-05-16","cited_by_count":19},{"id":"2505.10554","title":"Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models","created":"2025-05-15","cited_by_count":18},{"id":"2502.12420","title":"Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models","created":"2025-02-18","cited_by_count":16},{"id":"2505.21178","title":"Walk Before You Run! Concise LLM Reasoning via Reinforcement Learning","created":"2025-05-27","cited_by_count":16},{"id":"2505.19716","title":"Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting","created":"2025-05-26","cited_by_count":15},{"id":"2409.14026","title":"Uncovering Latent Chain of Thought Vectors in Language Models","created":"2024-09-21","cited_by_count":14},{"id":"2504.09923","title":"Guiding Reasoning in Small Language Models with LLM Assistance","created":"2025-04-14","cited_by_count":14},{"id":"2503.24198","title":"TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers' Guidance","created":"2025-03-31","cited_by_count":11},{"id":"2506.12473","title":"TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks","created":"2025-06-14","cited_by_count":9},{"id":"2506.04182","title":"Long or short CoT? Investigating Instance-level Switch of Large Reasoning Models","created":"2025-06-04","cited_by_count":8},{"id":"2502.10749","title":"LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging","created":"2025-02-15","cited_by_count":7},{"id":"2505.12992","title":"Fractured Chain-of-Thought Reasoning","created":"2025-05-19","cited_by_count":7},{"id":"2506.11578","title":"Efficient LLM Collaboration via Planning","created":"2025-06-13","cited_by_count":7},{"id":"2503.18891","title":"AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration","created":"2025-03-24","cited_by_count":6},{"id":"2505.22095","title":"Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation","created":"2025-05-28","cited_by_count":6},{"id":"2505.07680","title":"SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models","created":"2025-05-12","cited_by_count":2},{"id":"2506.03566","title":"POSS: Position Specialist Generates Better Draft for Speculative Decoding","created":"2025-06-04","cited_by_count":2}],"next_cursor":null}