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

@inproceedings{aaai2026_u2udata_100107,
  title = {{U2UData+: A Scalable Swarm UAVs Autonomous Flight Dataset for Embodied Long-horizon Tasks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37158},
}

@inproceedings{aaai2026_mcptox_108543,
  title = {{MCPTox: A Benchmark for Tool Poisoning on Real-World MCP Servers}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40895},
}

@inproceedings{neurips2023_de_66584,
  title = {{De novo Drug Design using Reinforcement Learning with Multiple GPT Agents}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73033},
}

@inproceedings{icml2025_itbench_48311,
  title = {{ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44303},
}

@inproceedings{neurips2025_wasp_76400,
  title = {{WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Ip1cCUAllL},
}

@inproceedings{icml2025_cradle_46167,
  title = {{Cradle: Empowering Foundation Agents towards General Computer Control}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46393},
}

@inproceedings{neurips2025_os_75923,
  title = {{OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Di30GwhQSX},
}

@inproceedings{iclr2025_swe_83640,
  title = {{SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28177},
}

@inproceedings{aaai2026_gittaskbench_108181,
  title = {{GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40533},
}

@inproceedings{icml2025_re_46027,
  title = {{RE-Bench: Evaluating Frontier AI R\&D Capabilities of Language Model Agents against Human Experts}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46519},
}

@inproceedings{neurips2025_stratus_78509,
  title = {{STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Clouds}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=fYW1PKawwJ},
}

@inproceedings{iclr2026_cybergym_84430,
  title = {{CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=2YvbLQEdYt},
}

@inproceedings{aaai2026_is_108528,
  title = {{IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40880},
}

@inproceedings{icml2024_anytool_45450,
  title = {{AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33001},
}

@inproceedings{icml2025_syncmind_46188,
  title = {{SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46372},
}

@inproceedings{icml2025_training_46530,
  title = {{Training Software Engineering Agents and Verifiers with SWE-Gym}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46038},
}

@inproceedings{icml2026_is_54570,
  title = {{Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=qG8g00zRZa},
}

@inproceedings{neurips2025_repo2run_78511,
  title = {{Repo2Run: Automated Building Executable Environment for Code Repository at Scale}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=fZsd3KLMje},
}

@inproceedings{neurips2025_bountybench_79430,
  title = {{BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=pIsP4lMlFd},
}

@inproceedings{iclr2025_eia_84036,
  title = {{EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/27789},
}

@inproceedings{iclr2026_st_86182,
  title = {{ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=MuCDzH0ctf},
}