% Key papers for Agent instruction-following benchmarks (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2024_lmdrive_23899,
  title = {{LMDrive: Closed-Loop End-to-End Driving with Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30531},
}

@inproceedings{aaai2024_expel_5894,
  title = {{ExpeL: LLM Agents Are Experiential Learners}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29936},
}

@inproceedings{neurips2024_mdagents_71190,
  title = {{MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96041},
}

@inproceedings{neurips2023_planbench_68536,
  title = {{PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73553},
}

@inproceedings{iclr2025_can_81820,
  title = {{Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29961},
}

@inproceedings{aaai2024_saycanpay_7259,
  title = {{SayCanPay: Heuristic Planning with Large Language Models Using Learnable Domain Knowledge}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29991},
}

@inproceedings{neurips2023_leveraging_70065,
  title = {{Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/69907},
}

@inproceedings{iclr2024_llmcarbon_34704,
  title = {{LLMCarbon: Modeling the End-to-End Carbon Footprint of Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18370},
}

@inproceedings{aaai2025_llm_9676,
  title = {{LLM-Powered User Simulator for Recommender System}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33456},
}

@inproceedings{iclr2024_large_35344,
  title = {{Large Language Models as Tool Makers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17729},
}

@inproceedings{cvpr2025_distilling_25967,
  title = {{Distilling Multi-modal Large Language Models for Autonomous Driving}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34067},
}

@inproceedings{aaai2024_confucius_5470,
  title = {{Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29759},
}

@inproceedings{iclr2024_mint_35067,
  title = {{MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18006},
}

@inproceedings{icml2024_travelplanner_45225,
  title = {{TravelPlanner: A Benchmark for Real-World Planning with Language Agents}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33227},
}

@inproceedings{neurips2024_embodied_73468,
  title = {{Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97552},
}

@inproceedings{cvpr2025_3d_25334,
  title = {{3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33422},
}

@inproceedings{aaai2025_open_10200,
  title = {{Open Models, Closed Minds? On Agents Capabilities in Mimicking Human Personalities through Open Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32125},
}

@inproceedings{neurips2024_large_73573,
  title = {{Large Language Models Play StarCraft II:Benchmarks and A Chain of Summarization Approach}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93911},
}

@inproceedings{iclr2026_llms_86912,
  title = {{LLMs Get Lost In Multi-Turn Conversation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=VKGTGGcwl6},
}

@inproceedings{aaai2025_planning_10313,
  title = {{Planning in the Dark: LLM-Symbolic Planning Pipeline Without Experts}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34855},
}

@inproceedings{neurips2024_leveraging_72204,
  title = {{Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95137},
}

@inproceedings{aaai2024_can_5370,
  title = {{Can LLMs Fix Issues with Reasoning Models? Towards More Likely Models for AI Planning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29984},
}