{"list":"other","total":59,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2402.14008","title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems","created":"2024-02-21","cited_by_count":1136},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2412.06769","title":"Training Large Language Models to Reason in a Continuous Latent Space","created":"2024-12-09","cited_by_count":797},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652},{"id":"2410.05229","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","created":"2024-10-07","cited_by_count":550},{"id":"2406.04692","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","created":"2024-06-07","cited_by_count":438},{"id":"2407.08693","title":"Robotic Control via Embodied Chain-of-Thought Reasoning","created":"2024-07-11","cited_by_count":346},{"id":"2502.18600","title":"Chain of Draft: Thinking Faster by Writing Less","created":"2025-02-25","cited_by_count":297},{"id":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294},{"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":"2410.07985","title":"Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models","created":"2024-10-10","cited_by_count":284},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268},{"id":"2402.12875","title":"Chain of Thought Empowers Transformers to Solve Inherently Serial Problems","created":"2024-02-20","cited_by_count":260},{"id":"2405.00451","title":"Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning","created":"2024-05-01","cited_by_count":241},{"id":"2502.21074","title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","created":"2025-02-28","cited_by_count":225},{"id":"2212.00193","title":"Distilling Reasoning Capabilities into Smaller Language Models","created":"2022-12-01","cited_by_count":158},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135},{"id":"2503.07572","title":"Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning","created":"2025-03-10","cited_by_count":123},{"id":"2504.05298","title":"One-Minute Video Generation with Test-Time Training","created":"2025-04-07","cited_by_count":101},{"id":"2503.21878","title":"Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment","created":"2025-03-27","cited_by_count":97},{"id":"2504.07086","title":"A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility","created":"2025-04-09","cited_by_count":93},{"id":"2503.06072","title":"A Survey on Post-training of Large Language Models","created":"2025-03-08","cited_by_count":54},{"id":"2411.17501","title":"The Limits of Inference Scaling Through Resampling","created":"2024-11-26","cited_by_count":53},{"id":"2104.06598","title":"AR-LSAT: Investigating Analytical Reasoning of Text","created":"2021-04-14","cited_by_count":51},{"id":"2310.07923","title":"The Expressive Power of Transformers with Chain of Thought","created":"2023-10-11","cited_by_count":50},{"id":"2504.15275","title":"Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning","created":"2025-04-21","cited_by_count":50},{"id":"2504.00869","title":"m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Models","created":"2025-04-01","cited_by_count":46},{"id":"2504.04736","title":"Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use","created":"2025-04-07","cited_by_count":45},{"id":"2502.18001","title":"Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning","created":"2025-02-25","cited_by_count":40},{"id":"2504.00810","title":"Z1: Efficient Test-time Scaling with Code","created":"2025-04-01","cited_by_count":35},{"id":"2502.21212","title":"Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought","created":"2025-02-28","cited_by_count":32},{"id":"2504.09772","title":"Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning","created":"2025-04-14","cited_by_count":29},{"id":"2503.23803","title":"Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute","created":"2025-03-31","cited_by_count":26},{"id":"2310.15147","title":"S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models","created":"2023-10-23","cited_by_count":18},{"id":"2502.12616","title":"Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions","created":"2025-02-18","cited_by_count":17},{"id":"2503.01461","title":"Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models","created":"2025-03-03","cited_by_count":13},{"id":"2406.17608","title":"Test-time generative augmentation for medical image segmentation","created":"2024-06-25","cited_by_count":6},{"id":"2410.09904","title":"Equitable Access to Justice: Logical LLMs Show Promise","created":"2024-10-13","cited_by_count":5},{"id":"2502.17717","title":"Knowledge Distillation with Training Wheels","created":"2025-02-24","cited_by_count":4},{"id":"2505.03320","title":"Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation","created":"2025-05-06","cited_by_count":3},{"id":"2412.08864","title":"GRIP: A Graph-Based Reasoning Instruction Producer","created":"2024-12-12","cited_by_count":2}],"next_cursor":null}