{"list":"other","total":57,"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":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"2412.16720","title":"OpenAI o1 System Card","created":"2024-12-21","cited_by_count":1244},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"2401.10774","title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","created":"2024-01-19","cited_by_count":843},{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559},{"id":"2507.19457","title":"GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning","created":"2025-07-25","cited_by_count":542},{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485},{"id":"2506.04178","title":"OpenThoughts: Data Recipes for Reasoning Models","created":"2025-06-04","cited_by_count":304},{"id":"2505.23281","title":"MathArena: Evaluating LLMs on Uncontaminated Math Competitions","created":"2025-05-29","cited_by_count":297},{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263},{"id":"2506.15841","title":"MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents","created":"2025-06-18","cited_by_count":238},{"id":"2505.24864","title":"ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models","created":"2025-05-30","cited_by_count":194},{"id":"2505.22312","title":"Skywork Open Reasoner 1 Technical Report","created":"2025-05-28","cited_by_count":165},{"id":"2412.09413","title":"Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems","created":"2024-12-12","cited_by_count":164},{"id":"2406.07394","title":"Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B","created":"2024-06-11","cited_by_count":158},{"id":"2510.11967","title":"Scaling Long-Horizon LLM Agent via Context-Folding","created":"2025-10-13","cited_by_count":148},{"id":"2512.08296","title":"Towards a Science of Scaling Agent Systems","created":"2025-12-09","cited_by_count":138},{"id":"2505.23885","title":"OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation","created":"2025-05-29","cited_by_count":131},{"id":"2505.19591","title":"Multi-Agent Collaboration via Evolving Orchestration","created":"2025-05-26","cited_by_count":108},{"id":"2307.15337","title":"Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation","created":"2023-07-28","cited_by_count":105},{"id":"2510.13786","title":"The Art of Scaling Reinforcement Learning Compute for LLMs","created":"2025-10-15","cited_by_count":101},{"id":"2505.17813","title":"Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning","created":"2025-05-23","cited_by_count":85},{"id":"2511.20639","title":"Latent Collaboration in Multi-Agent Systems","created":"2025-11-25","cited_by_count":73},{"id":"2512.16649","title":"JustRL: Scaling a 1.5B LLM with a Simple RL Recipe","created":"2025-12-18","cited_by_count":64},{"id":"2509.07980","title":"Parallel-R1: Towards Parallel Thinking via Reinforcement Learning","created":"2025-09-09","cited_by_count":61},{"id":"2506.09026","title":"e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs","created":"2025-06-10","cited_by_count":59},{"id":"2504.15466","title":"Learning Adaptive Parallel Reasoning with Language Models","created":"2025-04-21","cited_by_count":58},{"id":"2508.08221","title":"Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning","created":"2025-08-11","cited_by_count":56},{"id":"2509.06870","title":"The Majority is not always right: RL training for solution aggregation","created":"2025-09-08","cited_by_count":47},{"id":"2407.10930","title":"Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together","created":"2024-07-15","cited_by_count":40},{"id":"2509.04475","title":"ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute","created":"2025-08-30","cited_by_count":38},{"id":"2510.15110","title":"DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning","created":"2025-10-16","cited_by_count":35},{"id":"2506.09014","title":"Learning to Reason Across Parallel Samples for LLM Reasoning","created":"2025-06-10","cited_by_count":32},{"id":"2509.06283","title":"SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents","created":"2025-09-08","cited_by_count":31},{"id":"2506.09991","title":"Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation","created":"2025-06-11","cited_by_count":30},{"id":"2505.18286","title":"Single-agent or Multi-agent Systems? Why Not Both?","created":"2025-05-23","cited_by_count":29},{"id":"2502.11517","title":"Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding","created":"2025-02-17","cited_by_count":28},{"id":"2503.17287","title":"FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient Training R1-like Reasoning Models","created":"2025-03-21","cited_by_count":27},{"id":"2510.01180","title":"BroRL: Scaling Reinforcement Learning via Broadened Exploration","created":"2025-10-01","cited_by_count":25},{"id":"2401.06761","title":"APAR: LLMs Can Do Auto-Parallel Auto-Regressive Decoding","created":"2024-01-12","cited_by_count":24},{"id":"2510.01123","title":"Rethinking Thinking Tokens: LLMs as Improvement Operators","created":"2025-10-01","cited_by_count":21},{"id":"2502.15964","title":"Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models","created":"2025-02-21","cited_by_count":20},{"id":"2512.07461","title":"Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning","created":"2025-12-08","cited_by_count":12},{"id":"2506.05745","title":"SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models","created":"2025-06-06","cited_by_count":10},{"id":"2512.01127","title":"Mode-Conditioning Unlocks Superior Test-Time Scaling","created":"2025-11-30","cited_by_count":8},{"id":"2510.26658","title":"The Era of Agentic Organization: Learning to Organize with Language Models","created":"2025-10-30","cited_by_count":7},{"id":"2508.04660","title":"Composing Policy Gradients and Prompt Optimization for Language Model Programs","created":"2025-08-06","cited_by_count":4}],"next_cursor":null}