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

@inproceedings{icml2019_learning_37502,
  title = {{Learning to Generalize from Sparse and Underspecified Rewards}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4332},
}

@inproceedings{icml2020_closed_38016,
  title = {{Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6335},
}

@inproceedings{neurips2025_learning_80033,
  title = {{Learning to Reason under Off-Policy Guidance}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=vO8LLoNWWk},
}

@inproceedings{neurips2025_open_76811,
  title = {{Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=NFM8F5cV0V},
}

@inproceedings{neurips2025_gui_74814,
  title = {{GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=1XLjrmKZ4p},
}

@inproceedings{neurips2025_stop_75021,
  title = {{Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=3Sxby0hH1q},
}

@inproceedings{neurips2025_reasoning_76214,
  title = {{Reasoning Gym: Reasoning Environments for Reinforcement Learning with Verifiable Rewards}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=GqYSunGmp7},
}

@inproceedings{aaai2026_medgr2_107773,
  title = {{MedGR2: Breaking the Data Barrier for Medical Reasoning via Generative Reward Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40125},
}

@inproceedings{icml2025_do_46060,
  title = {{Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46497},
}

@inproceedings{icml2025_multi_47794,
  title = {{Multi-Turn Code Generation Through Single-Step Rewards}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44806},
}

@inproceedings{icml2025_mona_48115,
  title = {{MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44493},
}

@inproceedings{icml2026_arenarl_49337,
  title = {{ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=1XUCkpEknR},
}

@inproceedings{icml2026_alternating_49540,
  title = {{Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=3SDg8dtkS8},
}

@inproceedings{icml2026_arlarena_50093,
  title = {{ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=90kxFi9VGP},
}

@inproceedings{icml2026_reward_50265,
  title = {{Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=AfqsNFzJcs},
}

@inproceedings{icml2026_dr_50393,
  title = {{Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=BvgmzJOn5M},
}

@inproceedings{icml2026_anchored_50641,
  title = {{Anchored Policy Optimization: Mitigating Exploration Collapse via Support-Constrained Rectification}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=EOEI74ZtA4},
}

@inproceedings{icml2026_rlanything_51169,
  title = {{RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=JLQV6NxS6W},
}

@inproceedings{icml2026_brorl_51311,
  title = {{BroRL: Scaling Reinforcement Learning via Broadened Exploration}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=KmS7pdFBEh},
}

@inproceedings{icml2026_on_51324,
  title = {{On the Emergence of Implicit Curriculum in RLVR Learning Dynamics}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=KxYCE98u1d},
}

@inproceedings{icml2026_shrinking_51388,
  title = {{Shrinking the Variance: Shrinkage Baselines for Reinforcement Learning with Verifiable Rewards}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=LffORETnav},
}

@inproceedings{icml2026_rate_51414,
  title = {{Rate or Fate? RLV\$^varepsilon\$R: Reinforcement Learning with Verifiable Noisy Rewards}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=LwB2EacVT6},
}