{"list":"other","total":51,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"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":"2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","created":"2023-09-28","cited_by_count":551},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464},{"id":"1609.05140","title":"The Option-Critic Architecture","created":"2016-09-16","cited_by_count":448},{"id":"2409.12917","title":"Training Language Models to Self-Correct via Reinforcement Learning","created":"2024-09-19","cited_by_count":426},{"id":"2207.00032","title":"DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale","created":"2022-06-30","cited_by_count":407},{"id":"2408.08435","title":"Automated Design of Agentic Systems","created":"2024-08-15","cited_by_count":407},{"id":"2503.01307","title":"Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs","created":"2025-03-03","cited_by_count":377},{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344},{"id":"1806.11532","title":"TextWorld: A Learning Environment for Text-based Games","created":"2018-06-29","cited_by_count":310},{"id":"2401.00595","title":"State of What Art? A Call for Multi-Prompt LLM Evaluation","created":"2023-12-31","cited_by_count":310},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301},{"id":"2312.03732","title":"A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA","created":"2023-11-28","cited_by_count":243},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200},{"id":"2503.09572","title":"Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks","created":"2025-03-12","cited_by_count":195},{"id":"2501.04682","title":"Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought","created":"2025-01-08","cited_by_count":109},{"id":"2304.03843","title":"Why think step by step? Reasoning emerges from the locality of experience","created":"2023-04-07","cited_by_count":103},{"id":"2405.04776","title":"Chain of Thoughtlessness? An Analysis of CoT in Planning","created":"2024-05-08","cited_by_count":103},{"id":"2506.07527","title":"Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions","created":"2025-06-09","cited_by_count":97},{"id":"2411.12580","title":"Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models","created":"2024-11-19","cited_by_count":41},{"id":"1702.06054","title":"Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning","created":"2017-02-20","cited_by_count":39},{"id":"2205.10816","title":"Chain of Thought Imitation with Procedure Cloning","created":"2022-05-22","cited_by_count":30},{"id":"2306.00323","title":"Thought Cloning: Learning to Think while Acting by Imitating Human Thinking","created":"2023-06-01","cited_by_count":30},{"id":"2406.00244","title":"Controlling Large Language Model Agents with Entropic Activation Steering","created":"2024-06-01","cited_by_count":29},{"id":"2306.03604","title":"Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach","created":"2023-06-06","cited_by_count":28},{"id":"2506.14045","title":"Discovering Temporal Structure: An Overview of Hierarchical Reinforcement Learning","created":"2025-06-16","cited_by_count":22},{"id":"2102.03718","title":"An Analysis of Frame-skipping in Reinforcement Learning","created":"2021-02-07","cited_by_count":18}],"next_cursor":null}