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

@inproceedings{iclr2021_measuring_30476,
  title = {{Measuring Massive Multitask Language Understanding}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2962},
}

@inproceedings{neurips2022_solving_64521,
  title = {{Solving Quantitative Reasoning Problems with Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54708},
}

@inproceedings{neurips2023_legalbench_68426,
  title = {{LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73565},
}

@inproceedings{neurips2023_c_68956,
  title = {{C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73516},
}

@inproceedings{neurips2023_faith_67487,
  title = {{Faith and Fate: Limits of Transformers on Compositionality}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72247},
}

@inproceedings{iclr2025_gsm_81150,
  title = {{GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30620},
}

@inproceedings{neurips2024_ctibench_73450,
  title = {{CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97556},
}

@inproceedings{iclr2024_let_35524,
  title = {{Let's Verify Step by Step}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17549},
}

@inproceedings{iclr2025_livecodebench_82766,
  title = {{LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29033},
}

@inproceedings{aaai2024_scieval_7271,
  title = {{SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29872},
}

@inproceedings{iclr2025_wizardmath_83343,
  title = {{WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28471},
}

@inproceedings{neurips2024_unveiling_70214,
  title = {{Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96872},
}

@inproceedings{icml2024_do_45177,
  title = {{Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33275},
}

@inproceedings{neurips2023_evaluating_68380,
  title = {{Evaluating Cognitive Maps and Planning in Large Language Models with CogEval}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71431},
}

@inproceedings{neurips2023_understanding_67064,
  title = {{Understanding Social Reasoning in Language Models with Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73680},
}

@inproceedings{neurips2024_charxiv_73055,
  title = {{CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97598},
}

@inproceedings{neurips2024_socraticlm_74049,
  title = {{SocraticLM: Exploring Socratic Personalized Teaching with Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93477},
}

@inproceedings{iclr2024_solving_34768,
  title = {{Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18306},
}

@inproceedings{icml2024_scibench_44831,
  title = {{SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33621},
}

@inproceedings{aaai2025_evaluating_9020,
  title = {{Evaluating Mathematical Reasoning Beyond Accuracy}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34987},
}

@inproceedings{aaai2025_argumentative_8143,
  title = {{Argumentative Large Language Models for Explainable and Contestable Claim Verification}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33637},
}

@inproceedings{iclr2024_hypothesis_34036,
  title = {{Hypothesis Search: Inductive Reasoning with Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19039},
}

@inproceedings{neurips2024_a_72158,
  title = {{A Careful Examination of Large Language Model Performance on Grade School Arithmetic}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97687},
}

@inproceedings{iclr2024_mathvista_34175,
  title = {{MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18900},
}

@inproceedings{neurips2024_gtbench_74601,
  title = {{GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic Evaluations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/92988},
}

@inproceedings{aaai2025_cyberpal_8580,
  title = {{CyberPal.AI: Empowering LLMs with Expert-Driven Cybersecurity Instructions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34618},
}

@inproceedings{neurips2024_lexeval_70754,
  title = {{LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97832},
}