mlsanityData to 14 Oct 2026

Skywork Open Reasoner 1 Technical Report

arXiv 2505.22312 ↗First posted 28 May 2025cs.LG cs.AI cs.CLcited by 165

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

The success of DeepSeek-R1 underscores the significant role of reinforcement learning (RL) in enhancing the reasoning capabilities of large language models (LLMs). In this work, we present Skywork-OR1, an effective and scalable RL implementation for long Chain-of-Thought (CoT) models. Building on the DeepSeek-R1-Distill model series, our RL approach achieves notable performance gains, increasing average accuracy across AIME24, AIME25, and LiveCodeBench from 57.8% to 72.8% (+15.0%) for the 32B model and from 43.6% to 57.5% (+13.9%) for the 7B model. Our Skywork-OR1-32B model surpasses both DeepSeek-R1 and Qwen3-32B on the AIME24 and AIME25 benchmarks, while achieving comparable results on LiveCodeBench. The Skywork-OR1-7B and Skywork-OR1-Math-7B models demonstrate competitive reasoning capabilities among models of similar size. We perform comprehensive ablation studies on the core components of our training pipeline to validate their effectiveness. Additionally, we thoroughly investigate the phenomenon of entropy collapse, identify key factors affecting entropy dynamics, and demonstrate that mitigating premature entropy collapse is critical for improved test performance. To support community research, we fully open-source our model weights, training code, and training datasets.

Key facts. Cited by 165 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 15 of its 36 references that are in the map. First posted on arXiv 28 May 2025.

Builds on

15 of 36 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Qwen3 Technical Report14 May
  2. 2025Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond13 Mar

Other references · 13

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2024Qwen2.5 Technical Reportcited by 4,942
  6. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  7. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  8. 2024OpenAI o1 System Cardcited by 1,244
  9. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  10. 2025VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Taskscited by 285
  11. 2025TTRL: Test-Time Reinforcement Learningcited by 275
  12. 2023TACO: Topics in Algorithmic COde generation datasetcited by 160
1 more
  1. 2025LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMscited by 70

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 80; 2026: 85.

165 papers.

Sort:

By area:

  1. 2025OpenThoughts: Data Recipes for Reasoning Modelscited by 304
  2. 2026Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipecited by 299
  3. 2025Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMscited by 289
  4. 2025Reasoning with Exploration: An Entropy Perspectivecited by 281
  5. 2025Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergycited by 214
  6. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  7. 2025Agentic Reinforced Policy Optimizationcited by 172
  8. 2025Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Modelscited by 138
  9. 2025Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoningcited by 104
  10. 2025Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RLcited by 80
  11. 2025AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergycited by 77
  12. 2025AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learningcited by 72
38 more
  1. 2025Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoningcited by 56
  2. 2025Intern-S1: A Scientific Multimodal Foundation Modelcited by 53
  3. 2025Rethinking Entropy Interventions in RLVR: An Entropy Change Perspectivecited by 52
  4. 2026SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weightingcited by 43
  5. 2025Reinforcement Pre-Trainingcited by 40
  6. 2025Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVRcited by 39
  7. 2025Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimizationcited by 39
  8. 2025LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinkingcited by 38
  9. 2025A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Modelscited by 38
  10. 2025Demystifying Reinforcement Learning in Agentic Reasoningcited by 33
  11. 2025EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modescited by 32
  12. 2026Trust Region On-Policy Distillationcited by 30
  13. 2025Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Modelscited by 28
  14. 2025Single-stream Policy Optimizationcited by 28
  15. 2026FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimizationcited by 25
  16. 2025CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignmentcited by 24
  17. 2025MedResearcher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Frameworkcited by 22
  18. 2025Differential Smoothing Mitigates Sharpening and Improves LLM Reasoningcited by 22
  19. 2025Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learningcited by 21
  20. 2025Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Modelscited by 21
  21. 2025When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RLcited by 21
  22. 2025Revisiting Entropy in Reinforcement Learning for Large Reasoning Modelscited by 21
  23. 2026SOD: Step-wise On-policy Distillation for Small Language Model Agentscited by 21
  24. 2025Revisiting LLM Reasoning via Information Bottleneckcited by 19
  25. 2025Don't Just Fine-tune the Agent, Tune the Environmentcited by 19
  26. 2025Trace Length is a Simple Uncertainty Signal in Reasoning Modelscited by 19
  27. 2025Generalizable End-to-End Tool-Use RL with Synthetic CodeGymcited by 17
  28. 2025EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learningcited by 17
  29. 2025AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agentcited by 17
  30. 2025DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPOcited by 17
  31. 2025From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligencecited by 15
  32. 2025Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Modelcited by 14
  33. 2025BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuningcited by 14
  34. 2025Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Modelscited by 13
  35. 2025EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Controlcited by 13
  36. 2026Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergencecited by 13
  37. 2026DOPD: Dual On-policy Distillationcited by 12
  38. 2025UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilitiescited by 11

50 most cited of 165 All 165 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Skywork-R1V3 Technical Report
  2. 2025100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models
  3. 2025An Empirical Study on Eliciting and Improving R1-like Reasoning Models
  4. 2025DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning
  5. 2025AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
  6. 2025Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models
  7. 2025SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild
  8. 2025R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model