% Key papers for RL for LLM reasoning (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2024_auto_22798,
  title = {{Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30069},
}

@inproceedings{iclr2023_reward_31933,
  title = {{Reward Design with Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/10964},
}

@inproceedings{iclr2025_training_81270,
  title = {{Training Language Models to Self-Correct via Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30501},
}

@inproceedings{icml2025_sft_47972,
  title = {{SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44633},
}

@inproceedings{aaai2026_ui_106509,
  title = {{UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38816},
}

@inproceedings{icml2024_preference_44814,
  title = {{Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33638},
}

@inproceedings{neurips2022_teacher_63748,
  title = {{Teacher Forcing Recovers Reward Functions for Text Generation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53950},
}

@inproceedings{neurips2025_group_77098,
  title = {{Group-in-Group Policy Optimization for LLM Agent Training}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=QXEhBMNrCW},
}

@inproceedings{iclr2025_rewarding_81119,
  title = {{Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30649},
}

@inproceedings{aaai2025_erfsl_8879,
  title = {{ERFSL: An Efficient Reward Function Searcher via Large Language Models for Custom-Environment Multi-Objective Reinforcement Learning (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35316},
}

@inproceedings{aaai2025_universal_11163,
  title = {{Universal Post-Processing Networks for Joint Optimization of Modules in Task-Oriented Dialogue Systems}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34681},
}

@inproceedings{icml2024_archer_44798,
  title = {{ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33654},
}

@inproceedings{icml2024_controlled_44813,
  title = {{Controlled Decoding from Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33639},
}

@inproceedings{icml2024_training_45572,
  title = {{Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32880},
}

@inproceedings{neurips2025_segment_75591,
  title = {{Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=9osvTOYbT4},
}

@inproceedings{aaai2021_adaptive_87,
  title = {{Adaptive Prior-Dependent Correction Enhanced Reinforcement Learning for Natural Language Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/12701-adaptive-prior-dependent-correction-enhanced-reinforcement-learning-for-natural-language-generation/},
}

@inproceedings{icml2024_furl_43740,
  title = {{FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34712},
}

@inproceedings{neurips2024_imitating_70535,
  title = {{Imitating Language via Scalable Inverse Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96578},
}

@inproceedings{neurips2025_reinforcement_74713,
  title = {{Reinforcement Learning Finetunes Small Subnetworks in Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=0NdS4xCngO},
}

@inproceedings{neurips2025_accelerating_77364,
  title = {{Accelerating RL for LLM Reasoning with Optimal Advantage Regression}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=T1V8BJO0iG},
}

@inproceedings{neurips2025_llm_77555,
  title = {{LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=VA5P0rUZPx},
}

@inproceedings{neurips2025_co_78019,
  title = {{Co-Reinforcement Learning for Unified Multimodal Understanding and Generation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=aDa0xEFDu1},
}

@inproceedings{iclr2026_the_85510,
  title = {{The Art of Scaling Reinforcement Learning Compute for LLMs}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=FMjeC9Msws},
}