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

@inproceedings{neurips2024_automix_73137,
  title = {{AutoMix: Automatically Mixing Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94293},
}

@inproceedings{iclr2024_hybrid_33450,
  title = {{Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19625},
}

@inproceedings{neurips2024_ensemble_70688,
  title = {{Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96435},
}

@inproceedings{neurips2024_autopsv_73156,
  title = {{AutoPSV: Automated Process-Supervised Verifier}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94275},
}

@inproceedings{neurips2024_greats_70255,
  title = {{GREATS: Online Selection of High-Quality Data for LLM Training in Every Iteration}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96834},
}

@inproceedings{icml2024_beyond_43259,
  title = {{Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35193},
}

@inproceedings{neurips2024_efficient_72825,
  title = {{Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94574},
}

@inproceedings{aaai2025_is_9608,
  title = {{Is There No Such Thing as a Bad Question? H4R: HalluciBot for Ratiocination, Rewriting, Ranking, and Routing}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34736},
}

@inproceedings{neurips2025_training_75664,
  title = {{Training Language Models to Reason Efficiently}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=AiZxn84Wdo},
}

@inproceedings{neurips2025_mess_80118,
  title = {{MESS+: Dynamically Learned Inference-Time LLM Routing in Model Zoos with Service Level Guarantees}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=wIM0y07NGX},
}

@inproceedings{iclr2025_multiagent_81693,
  title = {{Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30086},
}

@inproceedings{aaai2026_deepor_108347,
  title = {{DeepOR: A Deep Reasoning Foundation Model for Optimization Modeling}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40699},
}

@inproceedings{aaai2025_s_10660,
  title = {{S^3cMath: Spontaneous Step-Level Self-Correction Makes Large Language Models Better Mathematical Reasoners}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34749},
}

@inproceedings{iclr2024_batchprompt_33834,
  title = {{BatchPrompt: Accomplish more with less}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19241},
}

@inproceedings{icml2026_optimal_54772,
  title = {{Optimal Self-Consistency for Efficient Reasoning with Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=sUTC7JE781},
}

@inproceedings{neurips2024_enhancing_70338,
  title = {{Enhancing Large Language Models through Adaptive Tokenizers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96759},
}

@inproceedings{neurips2025_scalable_74881,
  title = {{Scalable Best-of-N Selection for Large Language Models via Self-Certainty}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=29FRqmVQK8},
}

@inproceedings{neurips2025_cost_75123,
  title = {{Cost-Aware Contrastive Routing for LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=4Qe2Hga43N},
}

@inproceedings{neurips2025_router_75910,
  title = {{Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=DWf4vroKWJ},
}

@inproceedings{neurips2025_bag_78197,
  title = {{Bag of Tricks for Inference-time Computation of LLM Reasoning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=c6OvkQTV2D},
}