{"list":"other","total":86,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"id":"2305.19118","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","created":"2023-05-30","cited_by_count":1011},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901},{"id":"2412.19437","title":"DeepSeek-V3 Technical Report","created":"2024-12-27","cited_by_count":811},{"id":"2412.06769","title":"Training Large Language Models to Reason in a Continuous Latent Space","created":"2024-12-09","cited_by_count":797},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711},{"id":"2503.06749","title":"Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models","created":"2025-03-09","cited_by_count":665},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2503.18892","title":"SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild","created":"2025-03-24","cited_by_count":511},{"id":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500},{"id":"2411.10440","title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","created":"2024-11-15","cited_by_count":454},{"id":"2501.05366","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","created":"2025-01-09","cited_by_count":433},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"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":"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":"2501.04519","title":"rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking","created":"2025-01-08","cited_by_count":313},{"id":"2212.09561","title":"Large Language Models are Better Reasoners with Self-Verification","created":"2022-12-19","cited_by_count":307},{"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":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284},{"id":"2412.18925","title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","created":"2024-12-25","cited_by_count":265},{"id":"2503.07536","title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","created":"2025-03-10","cited_by_count":248},{"id":"2302.08468","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","created":"2023-02-16","cited_by_count":239},{"id":"2405.14838","title":"From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step","created":"2024-05-23","cited_by_count":235},{"id":"2307.04964","title":"Secrets of RLHF in Large Language Models Part I: PPO","created":"2023-07-11","cited_by_count":229},{"id":"2501.06848","title":"A General Framework for Inference-time Scaling and Steering of Diffusion Models","created":"2025-01-12","cited_by_count":224},{"id":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198},{"id":"2412.18319","title":"Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search","created":"2024-12-24","cited_by_count":175},{"id":"2401.06080","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","created":"2024-01-11","cited_by_count":171},{"id":"2501.18427","title":"SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer","created":"2025-01-30","cited_by_count":165},{"id":"2407.06023","title":"Distilling System 2 into System 1","created":"2024-07-08","cited_by_count":159},{"id":"2501.06186","title":"LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs","created":"2025-01-10","cited_by_count":147},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135},{"id":"2409.18486","title":"Evaluation of OpenAI o1: Opportunities and Challenges of AGI","created":"2024-09-27","cited_by_count":127},{"id":"2503.05179","title":"Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching","created":"2025-03-07","cited_by_count":117},{"id":"2502.12143","title":"Small Models Struggle to Learn from Strong Reasoners","created":"2025-02-17","cited_by_count":113},{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112},{"id":"2502.04644","title":"Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools","created":"2025-02-07","cited_by_count":106},{"id":"2502.02542","title":"OverThink: Slowdown Attacks on Reasoning LLMs","created":"2025-02-04","cited_by_count":96},{"id":"2410.09671","title":"OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models","created":"2024-10-12","cited_by_count":94},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91},{"id":"2410.02884","title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning","created":"2024-10-03","cited_by_count":91},{"id":"2412.00154","title":"o1-Coder: an o1 Replication for Coding","created":"2024-11-29","cited_by_count":78},{"id":"2503.04548","title":"An Empirical Study on Eliciting and Improving R1-like Reasoning Models","created":"2025-03-06","cited_by_count":78},{"id":"2412.01928","title":"MALT: Improving Reasoning with Multi-Agent LLM Training","created":"2024-12-02","cited_by_count":76},{"id":"2502.04128","title":"Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis","created":"2025-02-06","cited_by_count":70},{"id":"2502.11271","title":"OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning","created":"2025-02-16","cited_by_count":69},{"id":"2501.11284","title":"RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?","created":"2025-01-20","cited_by_count":60},{"id":"2502.18482","title":"MixLLM: Dynamic Routing in Mixed Large Language Models","created":"2025-02-09","cited_by_count":59},{"id":"2504.10081","title":"RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability","created":"2025-04-14","cited_by_count":59},{"id":"2411.18478","title":"Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS","created":"2024-11-27","cited_by_count":54},{"id":"2408.08862","title":"Visual Agents as Fast and Slow Thinkers","created":"2024-08-16","cited_by_count":53},{"id":"2306.00024","title":"Self-Verification Improves Few-Shot Clinical Information Extraction","created":"2023-05-30","cited_by_count":52},{"id":"2410.08328","title":"Agents Thinking Fast and Slow: A Talker-Reasoner Architecture","created":"2024-10-10","cited_by_count":36},{"id":"2503.16212","title":"MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion","created":"2025-03-20","cited_by_count":30},{"id":"2412.17498","title":"DRT: Deep Reasoning Translation via Long Chain-of-Thought","created":"2024-12-23","cited_by_count":29},{"id":"2312.07622","title":"Mathematical Language Models: A Survey","created":"2023-12-12","cited_by_count":24},{"id":"2502.13943","title":"AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence","created":"2025-02-19","cited_by_count":24},{"id":"2502.03860","title":"BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation","created":"2025-02-06","cited_by_count":23},{"id":"2503.02324","title":"PromptCoT: Synthesizing Olympiad-level Problems for Mathematical Reasoning in Large Language Models","created":"2025-03-04","cited_by_count":22},{"id":"2502.08482","title":"Enhancing Auto-regressive Chain-of-Thought through Loop-Aligned Reasoning","created":"2025-02-12","cited_by_count":19},{"id":"2308.09658","title":"Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning","created":"2023-08-18","cited_by_count":17},{"id":"2411.11930","title":"AtomThink: Multimodal Slow Thinking with Atomic Step Reasoning","created":"2024-11-18","cited_by_count":17},{"id":"2305.13016","title":"Iterative Forward Tuning Boosts In-Context Learning in Language Models","created":"2023-05-22","cited_by_count":15},{"id":"2406.12295","title":"Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding","created":"2024-06-18","cited_by_count":13},{"id":"2409.17433","title":"HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows","created":"2024-09-25","cited_by_count":13},{"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},{"id":"2411.11053","title":"SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation","created":"2024-11-17","cited_by_count":10},{"id":"2502.11525","title":"Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs","created":"2025-02-17","cited_by_count":7},{"id":"2502.14628","title":"PEARL: Towards Permutation-Resilient LLMs","created":"2025-02-20","cited_by_count":6},{"id":"2504.04942","title":"Lemmanaid: Neuro-Symbolic Lemma Conjecturing","created":"2025-04-07","cited_by_count":6},{"id":"2502.12929","title":"Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options","created":"2025-02-18","cited_by_count":3},{"id":"2411.04799","title":"Kwai-STaR: Transform LLMs into State-Transition Reasoners","created":"2024-11-07","cited_by_count":1}],"next_cursor":null}