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

@inproceedings{aaai2025_analogcoder_8120,
  title = {{AnalogCoder: Analog Circuit Design via Training-Free Code Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32016},
}

@inproceedings{aaai2025_cve_8372,
  title = {{CVE-LLM: Ontology-Assisted Automatic Vulnerability Evaluation Using Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35139},
}

@inproceedings{aaai2025_magic_9830,
  title = {{MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQL}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34511},
}

@inproceedings{neurips2023_intercode_68988,
  title = {{InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73513},
}

@inproceedings{iclr2024_repobench_35297,
  title = {{RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17776},
}

@inproceedings{cvpr2025_eee_26057,
  title = {{EEE-Bench: A Comprehensive Multimodal Electrical And Electronics Engineering Benchmark}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35039},
}

@inproceedings{neurips2023_crosscodeeval_69911,
  title = {{CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73423},
}

@inproceedings{neurips2025_autoredteamer_80219,
  title = {{AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=xQH4lDLIC0},
}

@inproceedings{neurips2024_redcode_73729,
  title = {{RedCode: Risky Code Execution and Generation Benchmark for Code Agents}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://openreview.net/forum?id=mAG68wdggA},
}

@inproceedings{neurips2024_apigen_71562,
  title = {{APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97756},
}

@inproceedings{icml2025_rlef_47229,
  title = {{RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45358},
}

@inproceedings{neurips2023_sheetcopilot_69746,
  title = {{SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70193},
}

@inproceedings{neurips2024_effibench_70315,
  title = {{EffiBench: Benchmarking the Efficiency of Automatically Generated Code}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97864},
}

@inproceedings{neurips2025_multi_76754,
  title = {{Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=MhBZzkz4h9},
}

@inproceedings{icml2025_swe_49051,
  title = {{SWE-Lancer: Can Frontier LLMs Earn \$1 Million from Real-World Freelance Software Engineering?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43573},
}

@inproceedings{neurips2024_spreadsheetbench_71616,
  title = {{SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97753},
}

@inproceedings{neurips2024_kgym_74638,
  title = {{kGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolution}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97426},
}

@inproceedings{iclr2026_mcp_87804,
  title = {{MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=fe8mzHwMxN},
}

@inproceedings{icml2025_repoaudit_47423,
  title = {{RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45170},
}

@inproceedings{neurips2024_easy2hard_73456,
  title = {{Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97554},
}

@inproceedings{neurips2024_nyu_73487,
  title = {{NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97547},
}

@inproceedings{neurips2024_trace_74102,
  title = {{Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93431},
}

@inproceedings{neurips2025_swe_76900,
  title = {{SWE-bench Goes Live!}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=OGWkr7gXka},
}