% Entries cite the listed source versions. arXiv dates are first submissions; other dates follow their cited records.

@misc{arxiv261005033,
  title = {{Code2Games: Enabling Coding Agents for Gaming World Generation}},
  author = {Wei Wu and Ziyang Xu and Zeyu Zhang and Yang Zhao and Hao Tang},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2610.05033},
  url = {https://arxiv.org/abs/2610.05033}
}

@misc{arxiv260937686,
  title = {{EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?}},
  author = {Hongcheng Gao and Hailong Qu and Yu Lei and Henghui Sun and Haoyang Li and Yipeng Wei and Naihao Xue and Xiaohan Yu and Zhuo Tao and Yihe Zang and Yajiao Wang and Jingyi Tang and Yi Li and Jingjing Zhou and Jie Luo and Bohan Zeng and Chengyu Shen and Hao Jiang and Chong Chen and Bowen Qu and Olive Huang and Zeqiang Wang},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2609.37686},
  url = {https://arxiv.org/abs/2609.37686}
}

@misc{arxiv260930604,
  title = {{The Hard Part Comes After Search: Benchmarking Web Agents on Synthesizing, Organizing, and Displaying Knowledge}},
  author = {Alexander Gill and Md Farhan Ishmam and Xuyen Nguyen and Neha Bhat and Parker Henry DeYoung and Fateme Hashemi Chaleshtori and Nathan Stringham and Kenneth Marino and Ana Marasović},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2609.30604},
  url = {https://arxiv.org/abs/2609.30604}
}

@misc{arxiv260916251,
  title = {{CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design}},
  author = {Zihan Dong and Yuanzhe Liu and Zhiyuan Ma and Qishi Zhan and Dehan Kong and Guohao Li and Kaixin Li},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2609.16251},
  url = {https://arxiv.org/abs/2609.16251}
}

@misc{arxiv260907712,
  title = {{APPSim-Bench: Bridging Real-world Apps and Reproducible Evaluation for Mobile GUI Agents}},
  author = {Jintian Feng and Long Chen and Xiao Yu and Jiayi Dai and Chenglong Liu and Haoru Wang and Zizhen Xue and Yuxuan Shi and Ziyang Wang and Yichen Gong},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2609.07712},
  url = {https://arxiv.org/abs/2609.07712}
}

@misc{arxiv260821833,
  title = {{GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?}},
  author = {Kun Chen and Haorong Hong and Peizhong Gao and Jianfeng Lin and Tongxu Luo and Yuxuan Xie and Chenxu Liu and Jieling He and Zhongyuan Liu and Zeno Zeng},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2608.21833},
  url = {https://arxiv.org/abs/2608.21833}
}

@misc{arxiv260704727,
  title = {{Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive Dashboards}},
  author = {Tianhao Niu and Ziyu Han and Qiguang Chen and Shiqi Zhou and Baocai Shan and Hengjie Fang and Qingfu Zhu and Wanxiang Che},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2607.04727},
  url = {https://arxiv.org/abs/2607.04727}
}

@misc{arxiv260703525,
  title = {{GameEngineBench: Evaluating Coding Agents on Real C++ Runtime Environments}},
  author = {Brian La and Sejoon Chang and Ben Kim and Junyoung Bae and Aamish Ahmad Beg and Sei Chang and Gonzalo Gonzalez-Pumariega and Kanav Goyal},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2607.03525},
  url = {https://arxiv.org/abs/2607.03525}
}

@misc{arxiv260629955,
  title = {{SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows}},
  author = {Jian Zhu and Yuzheng Zhang and Zeyao Ma and Bohan Zhang and Armin Schoepf and Daniel Woloch and Peter Yiliu Wang and Guangyu Robert Yang and Samuel Jacob and Siddharth Nagisetty and Abhiram Chundru and Jean Lin and Spencer Mateega and Jing Zhang},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2606.29955},
  url = {https://arxiv.org/abs/2606.29955}
}

@misc{arxiv260629537,
  title = {{OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks}},
  author = {Mengqi Yuan and Zilong Zhou and Xinzhuang Xiong and Weiming Wu and Jiayang Sun and Jiamin Song and Kaiqian Cui and Bowen Wang and Haoyuan Wu and Yitong Li and Dunjie Lu and Haikong Lu and Qi Zhen and Xinyuan Wang and Jiaqi Deng and Yuhao Yang and Cheng Chen and Boyuan Zheng and Alex Su and Xiao Yu and Hao Zou and Saaket Agashe and Xing Han Lu and Manpreet Kaur and Zhengyang Qi and Vincent Sunn Chen and Frederic Sala and Dayiheng Liu and Junyang Lin and Zhou Yu and Yu Su and Siva Reddy and Xin Eric Wang and Peng Qi and Tianbao Xie and Tao Yu},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2606.29537},
  url = {https://arxiv.org/abs/2606.29537}
}

@misc{arxiv260617861,
  title = {{GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?}},
  author = {Tongxu Luo and Rongsheng Wang and Jiaxi Bi and Chenming Xu and Zhengyang Tang and Jianlong Chen and Juhao Liang and Ke Ji and Shuqi Guo and Yuhao Du and Fan Bu and Wenyu Du and Xiaotong Zhang and Kyle Li and Shaobo Wang and Linfeng Zhang and Yuxuan Liu and Xin Lai and Chenxin Li and Yiduo Guo and Zhexin Zhang and Xinyuan Wang and Tianyi Bai and Ziniu Li and Benyou Wang},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2606.17861},
  url = {https://arxiv.org/abs/2606.17861}
}

@misc{arxiv260609764,
  title = {{iOSWorld: A Benchmark for Personally Intelligent Phone Agents}},
  author = {Lawrence Keunho Jang and Mareks Woodside and Geronimo Carom and Andrew Keunwoo Jang and Jing Yu Koh and Ruslan Salakhutdinov},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2606.09764},
  url = {https://arxiv.org/abs/2606.09764}
}

@misc{arxiv260606560,
  title = {{MacArena: Benchmarking Computer Use Agents on an Online macOS Environment}},
  author = {Victor Muryn and Maksym Shamrai and Sofiia Mazepa and Yehor Khodysko},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2606.06560},
  url = {https://arxiv.org/abs/2606.06560}
}

@misc{arxiv260603103,
  title = {{DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration}},
  author = {Wenkai Wang and Tao Xiong and Jingchen Ni and Yunpeng Bao and Xiyun Li and Tianqi Liu and Hongcan Guo and Zilong Huang and Shengyu Zhang},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2606.03103},
  url = {https://arxiv.org/abs/2606.03103}
}

@misc{arxiv260418394,
  title = {{OpenGame: Open Agentic Coding for Games}},
  author = {Yilei Jiang and Jinyuan Hu and Qianyin Xiao and Yaozhi Zheng and Ruize Ma and Kaituo Feng and Jiaming Han and Tianshuo Peng and Kaixuan Fan and Manyuan Zhang and Xiangyu Yue},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2604.18394},
  url = {https://arxiv.org/abs/2604.18394}
}

@misc{arxiv260408523,
  title = {{ClawBench: Can AI Agents Complete Everyday Online Tasks?}},
  author = {Yuxuan Zhang and Yubo Wang and Yipeng Zhu and Penghui Du and Junwen Miao and Xuan Lu and Zhuofeng Li and Xingwei Qu and Zhengkang Guo and Yuanzhe Shen and Dingjie Song and Han Zhou and Tuney Zheng and Xian Wu and Hao Yu and Songcheng Cai and Yi Lu and Yunzhuo Hao and Minyi Lei and Liang Chen and Kai Zou and Huifeng Yin and Wendong Xu and Dongfu Jiang and Ping Nie and Jiaheng Liu and Wenhu Chen and Kelsey R. Allen},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2604.08523},
  url = {https://arxiv.org/abs/2604.08523}
}

@misc{arxiv260304949,
  title = {{TimeWarp: Evaluating Web Agents by Revisiting the Past}},
  author = {Md Farhan Ishmam and Kenneth Marino},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2603.04949},
  url = {https://arxiv.org/abs/2603.04949}
}

@misc{arxiv260211964,
  title = {{Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments}},
  author = {Romain Froger and Pierre Andrews and Matteo Bettini and Amar Budhiraja and Ricardo Silveira Cabral and Virginie Do and Emilien Garreau and Jean-Baptiste Gaya and Hugo Laurençon and Maxime Lecanu and Kunal Malkan and Dheeraj Mekala and Pierre Ménard and Gerard Moreno-Torres Bertran and Ulyana Piterbarg and Mikhail Plekhanov and Mathieu Rita and Andrey Rusakov and Vladislav Vorotilov and Mengjue Wang and Ian Yu and Amine Benhalloum and Grégoire Mialon and Thomas Scialom},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2602.11964},
  url = {https://arxiv.org/abs/2602.11964}
}

@misc{arxiv260211103,
  title = {{GameDevBench: Evaluating Agentic Capabilities Through Game Development}},
  author = {Wayne Chi and Yixiong Fang and Arnav Yayavaram and Siddharth Yayavaram and Seth Karten and Qiuhong Anna Wei and Runkun Chen and Alexander Wang and Valerie Chen and Ameet Talwalkar and Chris Donahue},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2602.11103},
  url = {https://arxiv.org/abs/2602.11103}
}

@misc{arxiv260210090,
  title = {{Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning}},
  author = {Zhaoyang Wang and Canwen Xu and Boyi Liu and Yite Wang and Siwei Han and Zhewei Yao and Huaxiu Yao and Yuxiong He},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2602.10090},
  url = {https://arxiv.org/abs/2602.10090}
}

@misc{arxiv260111868,
  title = {{Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces}},
  author = {Mike A. Merrill and Alexander G. Shaw and Nicholas Carlini and Boxuan Li and Harsh Raj and Ivan Bercovich and Lin Shi and Jeong Yeon Shin and Thomas Walshe and E. Kelly Buchanan and Junhong Shen and Guanghao Ye and Haowei Lin and Jason Poulos and Maoyu Wang and Marianna Nezhurina and Jenia Jitsev and Di Lu and Orfeas Menis Mastromichalakis and Zhiwei Xu and Zizhao Chen and Yue Liu and Robert Zhang and Leon Liangyu Chen and Anurag Kashyap and Jan-Lucas Uslu and Jeffrey Li and Jianbo Wu and Minghao Yan and Song Bian and Vedang Sharma and Ke Sun and Steven Dillmann and Akshay Anand and Andrew Lanpouthakoun and Bardia Koopah and Changran Hu and Etash Guha and Gabriel H. S. Dreiman and Jiacheng Zhu and Karl Krauth and Li Zhong and Niklas Muennighoff and Robert Amanfu and Shangyin Tan and Shreyas Pimpalgaonkar and Tushar Aggarwal and Xiangning Lin and Xin Lan and Xuandong Zhao and Yiqing Liang and Yuanli Wang and Zilong Wang and Changzhi Zhou and David Heineman and Hange Liu and Harsh Trivedi and John Yang and Junhong Lin and Manish Shetty and Michael Yang and Nabil Omi and Negin Raoof and Shanda Li and Terry Yue Zhuo and Wuwei Lin and Yiwei Dai and Yuxin Wang and Wenhao Chai and Shang Zhou and Dariush Wahdany and Ziyu She and Jiaming Hu and Zhikang Dong and Yuxuan Zhu and Sasha Cui and Ahson Saiyed and Arinbjörn Kolbeinsson and Jesse Hu and Christopher Michael Rytting and Ryan Marten and Yixin Wang and Alex Dimakis and Andy Konwinski and Ludwig Schmidt},
  year = {2026},
  archivePrefix = {arXiv},
  eprint = {2601.11868},
  url = {https://arxiv.org/abs/2601.11868}
}

@misc{arxiv251120766,
  title = {{OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability}},
  author = {Karen Ullrich and Jingtong Su and Claudia Shi and Arjun Subramonian and Amir Bar and Ivan Evtimov and Nikolaos Tsilivis and Randall Balestriero and Julia Kempe and Mark Ibrahim},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2511.20766},
  url = {https://arxiv.org/abs/2511.20766}
}

@misc{arxiv251024411,
  title = {{OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows}},
  author = {Qiushi Sun and Mukai Li and Zhoumianze Liu and Zhihui Xie and Fangzhi Xu and Zhangyue Yin and Kanzhi Cheng and Zehao Li and Zichen Ding and Qi Liu and Zhiyong Wu and Zhuosheng Zhang and Ben Kao and Lingpeng Kong},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2510.24411},
  url = {https://arxiv.org/abs/2510.24411}
}

@misc{arxiv251005318,
  title = {{BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions}},
  author = {Nan Huo and Xiaohan Xu and Jinyang Li and Per Jacobsson and Shipei Lin and Bowen Qin and Binyuan Hui and Xiaolong Li and Ge Qu and Shuzheng Si and Linheng Han and Edward Alexander and Xintong Zhu and Rui Qin and Ruihan Yu and Yiyao Jin and Feige Zhou and Weihao Zhong and Yun Chen and Hongyu Liu and Chenhao Ma and Fatma Ozcan and Yannis Papakonstantinou and Reynold Cheng},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2510.05318},
  url = {https://arxiv.org/abs/2510.05318}
}

@misc{arxiv250924709,
  title = {{IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?}},
  author = {Yang Chen and Minghao Liu and Yufan Shen and Yunwen Li and Tianyuan Huang and Xinyu Fang and Tianyu Zheng and Wenxuan Huang and Cheng Yang and Daocheng Fu and Jianbiao Mei and Rong Wu and Yunfei Zhao and Licheng Wen and Xuemeng Yang and Song Mao and Qunshu Lin and Zhi Yu and Yongliang Shen and Yu Qiao and Botian Shi},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2509.24709},
  url = {https://arxiv.org/abs/2509.24709}
}

@misc{arxiv250920136,
  title = {{V-GameGym: Visual Game Generation for Code Large Language Models}},
  author = {Wei Zhang and Jack Yang and Renshuai Tao and Lingzheng Chai and Shawn Guo and Jiajun Wu and Xiaoming Chen and Ganqu Cui and Ning Ding and Xander Xu and Hu Wei and Bowen Zhou},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2509.20136},
  url = {https://arxiv.org/abs/2509.20136}
}

@misc{arxiv250917158,
  title = {{ARE: Scaling Up Agent Environments and Evaluations}},
  author = {Romain Froger and Pierre Andrews and Matteo Bettini and Amar Budhiraja and Ricardo Silveira Cabral and Virginie Do and Emilien Garreau and Jean-Baptiste Gaya and Hugo Laurençon and Maxime Lecanu and Kunal Malkan and Dheeraj Mekala and Pierre Ménard and Gerard Moreno-Torres Bertran and Ulyana Piterbarg and Mikhail Plekhanov and Mathieu Rita and Andrey Rusakov and Vladislav Vorotilov and Mengjue Wang and Ian Yu and Amine Benhalloum and Grégoire Mialon and Thomas Scialom},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2509.17158},
  url = {https://arxiv.org/abs/2509.17158}
}

@misc{arxiv250916941,
  title = {{SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?}},
  author = {Xiang Deng and Jeff Da and Edwin Pan and Yannis Yiming He and Charles Ide and Kanak Garg and Niklas Lauffer and Andrew Park and Nitin Pasari and Chetan Rane and Karmini Sampath and Maya Krishnan and Srivatsa Kundurthy and Sean Hendryx and Zifan Wang and Vijay Bharadwaj and Jeff Holm and Raja Aluri and Chen Bo Calvin Zhang and Noah Jacobson and Bing Liu and Brad Kenstler},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2509.16941},
  url = {https://arxiv.org/abs/2509.16941}
}

@misc{arxiv250908755,
  title = {{AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning}},
  author = {Zhiheng Xi and Jixuan Huang and Chenyang Liao and Baodai Huang and Honglin Guo and Jiaqi Liu and Rui Zheng and Junjie Ye and Jiazheng Zhang and Wenxiang Chen and Wei He and Yiwen Ding and Guanyu Li and Zehui Chen and Zhengyin Du and Xuesong Yao and Yufei Xu and Jiecao Chen and Tao Gui and Zuxuan Wu and Qi Zhang and Xuanjing Huang and Yu-Gang Jiang},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2509.08755},
  url = {https://arxiv.org/abs/2509.08755}
}

@misc{arxiv250813024,
  title = {{WebMall -- A Multi-Shop Benchmark for Evaluating Web Agents}},
  author = {Ralph Peeters and Aaron Steiner and Luca Schwarz and Julian Yuya Caspary and Christian Bizer},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2508.13024},
  url = {https://arxiv.org/abs/2508.13024}
}

@misc{arxiv250809123,
  title = {{OpenCUA: Open Foundations for Computer-Use Agents}},
  author = {Xinyuan Wang and Bowen Wang and Dunjie Lu and Junlin Yang and Tianbao Xie and Junli Wang and Jiaqi Deng and Xiaole Guo and Yiheng Xu and Chen Henry Wu and Zhennan Shen and Zhuokai Li and Ryan Li and Xiaochuan Li and Junda Chen and Boyuan Zheng and Peihang Li and Fangyu Lei and Ruisheng Cao and Yeqiao Fu and Dongchan Shin and Martin Shin and Jiarui Hu and Yuyan Wang and Jixuan Chen and Yuxiao Ye and Danyang Zhang and Dikang Du and Hao Hu and Huarong Chen and Zaida Zhou and Haotian Yao and Ziwei Chen and Qizheng Gu and Yipu Wang and Heng Wang and Diyi Yang and Victor Zhong and Flood Sung and Y. Charles and Zhilin Yang and Tao Yu},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2508.09123},
  url = {https://arxiv.org/abs/2508.09123}
}

@misc{arxiv250715887,
  title = {{AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?}},
  author = {Ori Press and Brandon Amos and Haoyu Zhao and Yikai Wu and Samuel K. Ainsworth and Dominik Krupke and Patrick Kidger and Touqir Sajed and Bartolomeo Stellato and Jisun Park and Nathanael Bosch and Eli Meril and Albert Steppi and Arman Zharmagambetov and Fangzhao Zhang and David Perez-Pineiro and Alberto Mercurio and Ni Zhan and Talor Abramovich and Kilian Lieret and Hanlin Zhang and Shirley Huang and Matthias Bethge and Ofir Press},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2507.15887},
  url = {https://arxiv.org/abs/2507.15887}
}

@misc{arxiv250623719,
  title = {{DABstep: Data Agent Benchmark for Multi-step Reasoning}},
  author = {Alex Egg and Martin Iglesias Goyanes and Friso Kingma and Andreu Mora and Leandro von Werra and Thomas Wolf},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2506.23719},
  url = {https://arxiv.org/abs/2506.23719}
}

@misc{arxiv250621506,
  title = {{Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge}},
  author = {Boyu Gou and Zanming Huang and Yuting Ning and Yu Gu and Michael Lin and Weijian Qi and Andrei Kopanev and Botao Yu and Bernal Jiménez Gutiérrez and Yiheng Shu and Chan Hee Song and Jiaman Wu and Shijie Chen and Hanane Nour Moussa and Tianshu Zhang and Jian Xie and Yifei Li and Tianci Xue and Zeyi Liao and Kai Zhang and Boyuan Zheng and Zhaowei Cai and Viktor Rozgic and Morteza Ziyadi and Huan Sun and Yu Su},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2506.21506},
  url = {https://arxiv.org/abs/2506.21506}
}

@misc{arxiv250616042,
  title = {{OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agents}},
  author = {Reyna Abhyankar and Qi Qi and Yiying Zhang},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2506.16042},
  url = {https://arxiv.org/abs/2506.16042}
}

@misc{arxiv250607982,
  title = {{τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment}},
  author = {Victor Barres and Honghua Dong and Soham Ray and Xujie Si and Karthik Narasimhan},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2506.07982},
  url = {https://arxiv.org/abs/2506.07982}
}

@misc{arxiv250607818,
  title = {{WebUIBench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in WebUI-to-Code}},
  author = {Zhiyu Lin and Zhengda Zhou and Zhiyuan Zhao and Tianrui Wan and Yilun Ma and Junyu Gao and Xuelong Li},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2506.07818},
  url = {https://arxiv.org/abs/2506.07818}
}

@misc{arxiv250601952,
  title = {{WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks}},
  author = {Atsuyuki Miyai and Zaiying Zhao and Kazuki Egashira and Atsuki Sato and Tatsumi Sunada and Shota Onohara and Hiromasa Yamanishi and Mashiro Toyooka and Kunato Nishina and Ryoma Maeda and Kiyoharu Aizawa and Toshihiko Yamasaki},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2506.01952},
  url = {https://arxiv.org/abs/2506.01952}
}

@misc{arxiv250519897,
  title = {{ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows}},
  author = {Qiushi Sun and Zhoumianze Liu and Chang Ma and Zichen Ding and Fangzhi Xu and Zhangyue Yin and Haiteng Zhao and Zhenyu Wu and Kanzhi Cheng and Zhaoyang Liu and Jianing Wang and Qintong Li and Xiangru Tang and Tianbao Xie and Xiachong Feng and Xiang Li and Ben Kao and Wenhai Wang and Biqing Qi and Lingpeng Kong and Zhiyong Wu},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2505.19897},
  url = {https://arxiv.org/abs/2505.19897}
}

@misc{arxiv250518878,
  title = {{CRMArena-Pro: Holistic Assessment of LLM Agents Across Diverse Business Scenarios and Interactions}},
  author = {Kung-Hsiang Huang and Akshara Prabhakar and Onkar Thorat and Divyansh Agarwal and Prafulla Kumar Choubey and Yixin Mao and Silvio Savarese and Caiming Xiong and Chien-Sheng Wu},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2505.18878},
  url = {https://arxiv.org/abs/2505.18878}
}

@misc{arxiv250503733,
  title = {{WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch}},
  author = {Zimu Lu and Yunqiao Yang and Houxing Ren and Haotian Hou and Han Xiao and Ke Wang and Weikang Shi and Aojun Zhou and Mingjie Zhan and Hongsheng Li},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2505.03733},
  url = {https://arxiv.org/abs/2505.03733}
}

@misc{arxiv250421798,
  title = {{SWE-smith: Scaling Data for Software Engineering Agents}},
  author = {John Yang and Kilian Lieret and Carlos E. Jimenez and Alexander Wettig and Kabir Khandpur and Yanzhe Zhang and Binyuan Hui and Ofir Press and Ludwig Schmidt and Diyi Yang},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2504.21798},
  url = {https://arxiv.org/abs/2504.21798}
}

@misc{arxiv250411442,
  title = {{TextArena}},
  author = {Leon Guertler and Bobby Cheng and Simon Yu and Bo Liu and Leshem Choshen and Cheston Tan},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2504.11442},
  url = {https://arxiv.org/abs/2504.11442}
}

@misc{arxiv250407981,
  title = {{ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use}},
  author = {Kaixin Li and Ziyang Meng and Hongzhan Lin and Ziyang Luo and Yuchen Tian and Jing Ma and Zhiyong Huang and Tat-Seng Chua},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2504.07981},
  url = {https://arxiv.org/abs/2504.07981}
}

@misc{arxiv250401786,
  title = {{BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing}},
  author = {Yunqi Gu and Ian Huang and Jihyeon Je and Guandao Yang and Leonidas Guibas},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2504.01786},
  url = {https://arxiv.org/abs/2504.01786}
}

@misc{arxiv250401382,
  title = {{An Illusion of Progress? Assessing the Current State of Web Agents}},
  author = {Tianci Xue and Weijian Qi and Tianneng Shi and Chan Hee Song and Boyu Gou and Dawn Song and Huan Sun and Yu Su},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2504.01382},
  url = {https://arxiv.org/abs/2504.01382}
}

@misc{arxiv250315661,
  title = {{UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction}},
  author = {Shravan Nayak and Xiangru Jian and Kevin Qinghong Lin and Juan A. Rodriguez and Montek Kalsi and Rabiul Awal and Nicolas Chapados and M. Tamer Özsu and Aishwarya Agrawal and David Vazquez and Christopher Pal and Perouz Taslakian and Spandana Gella and Sai Rajeswar},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2503.15661},
  url = {https://arxiv.org/abs/2503.15661}
}

@misc{arxiv250300096,
  title = {{BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology}},
  author = {Ludovico Mitchener and Jon M Laurent and Alex Andonian and Benjamin Tenmann and Siddharth Narayanan and Geemi P Wellawatte and Andrew White and Lorenzo Sani and Samuel G Rodriques},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2503.00096},
  url = {https://arxiv.org/abs/2503.00096}
}

@misc{arxiv250214499,
  title = {{MLGym: A New Framework and Benchmark for Advancing AI Research Agents}},
  author = {Deepak Nathani and Lovish Madaan and Nicholas Roberts and Nikolay Bashlykov and Ajay Menon and Vincent Moens and Amar Budhiraja and Despoina Magka and Vladislav Vorotilov and Gaurav Chaurasia and Dieuwke Hupkes and Ricardo Silveira Cabral and Tatiana Shavrina and Jakob Foerster and Yoram Bachrach and William Yang Wang and Roberta Raileanu},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2502.14499},
  url = {https://arxiv.org/abs/2502.14499}
}

@misc{arxiv250212115,
  title = {{SWE-Lancer: Can Frontier LLMs Earn \$1 Million from Real-World Freelance Software Engineering?}},
  author = {Samuel Miserendino and Michele Wang and Tejal Patwardhan and Johannes Heidecke},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2502.12115},
  url = {https://arxiv.org/abs/2502.12115}
}

@misc{arxiv250208047,
  title = {{WorldGUI: An Interactive Benchmark for Desktop GUI Automation from Any Starting Point}},
  author = {Henry Hengyuan Zhao and Kaiming Yang and Wendi Yu and Difei Gao and Mike Zheng Shou},
  year = {2025},
  archivePrefix = {arXiv},
  eprint = {2502.08047},
  url = {https://arxiv.org/abs/2502.08047}
}

@misc{webarenaverifiedopenreview,
  title = {{WebArena Verified: Reliable Evaluation for Web Agents}},
  author = {Amine El hattami and Megh Thakkar and Nicolas Chapados and Christopher Pal},
  year = {2025},
  howpublished = {OpenReview},
  note = {Workshop on Scaling Environments for Agents, NeurIPS 2025},
  url = {https://openreview.net/forum?id=94tlGxmqkN}
}

@misc{arxiv241221139,
  title = {{Training Software Engineering Agents and Verifiers with SWE-Gym}},
  author = {Jiayi Pan and Xingyao Wang and Graham Neubig and Navdeep Jaitly and Heng Ji and Alane Suhr and Yizhe Zhang},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2412.21139},
  url = {https://arxiv.org/abs/2412.21139}
}

@misc{arxiv241214161,
  title = {{TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks}},
  author = {Frank F. Xu and Yufan Song and Boxuan Li and Yuxuan Tang and Kritanjali Jain and Mengxue Bao and Zora Z. Wang and Xuhui Zhou and Zhitong Guo and Murong Cao and Mingyang Yang and Hao Yang Lu and Amaad Martin and Zhe Su and Leander Maben and Raj Mehta and Wayne Chi and Lawrence Jang and Yiqing Xie and Shuyan Zhou and Graham Neubig},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2412.14161},
  url = {https://arxiv.org/abs/2412.14161}
}

@misc{arxiv241205467,
  title = {{The BrowserGym Ecosystem for Web Agent Research}},
  author = {Thibault Le Sellier De Chezelles and Maxime Gasse and Alexandre Drouin and Massimo Caccia and Léo Boisvert and Megh Thakkar and Tom Marty and Rim Assouel and Sahar Omidi Shayegan and Lawrence Keunho Jang and Xing Han Lù and Ori Yoran and Dehan Kong and Frank F. Xu and Siva Reddy and Quentin Cappart and Graham Neubig and Ruslan Salakhutdinov and Nicolas Chapados and Alexandre Lacoste},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2412.05467},
  url = {https://arxiv.org/abs/2412.05467}
}

@misc{arxiv241113543,
  title = {{BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games}},
  author = {Davide Paglieri and Bartłomiej Cupiał and Samuel Coward and Ulyana Piterbarg and Maciej Wolczyk and Akbir Khan and Eduardo Pignatelli and Łukasz Kuciński and Lerrel Pinto and Rob Fergus and Jakob Nicolaus Foerster and Jack Parker-Holder and Tim Rocktäschel},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2411.13543},
  url = {https://arxiv.org/abs/2411.13543}
}

@misc{arxiv241103292,
  title = {{Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping}},
  author = {Jingyu Xiao and Yuxuan Wan and Yintong Huo and Zixin Wang and Xinyi Xu and Wenxuan Wang and Zhiyao Xu and Yuhang Wang and Michael R. Lyu},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2411.03292},
  url = {https://arxiv.org/abs/2411.03292}
}

@misc{arxiv241102305,
  title = {{CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments}},
  author = {Kung-Hsiang Huang and Akshara Prabhakar and Sidharth Dhawan and Yixin Mao and Huan Wang and Silvio Savarese and Caiming Xiong and Philippe Laban and Chien-Sheng Wu},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2411.02305},
  url = {https://arxiv.org/abs/2411.02305}
}

@misc{arxiv241024024,
  title = {{AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents}},
  author = {Yifan Xu and Xiao Liu and Xueqiao Sun and Siyi Cheng and Hao Yu and Hanyu Lai and Shudan Zhang and Dan Zhang and Jie Tang and Yuxiao Dong},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2410.24024},
  url = {https://arxiv.org/abs/2410.24024}
}

@misc{arxiv241023218,
  title = {{OS-ATLAS: A Foundation Action Model for Generalist GUI Agents}},
  author = {Zhiyong Wu and Zhenyu Wu and Fangzhi Xu and Yian Wang and Qiushi Sun and Chengyou Jia and Kanzhi Cheng and Zichen Ding and Liheng Chen and Paul Pu Liang and Yu Qiao},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2410.23218},
  url = {https://arxiv.org/abs/2410.23218}
}

@misc{arxiv241015164,
  title = {{SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation}},
  author = {Jingxuan Chen and Derek Yuen and Bin Xie and Yuhao Yang and Gongwei Chen and Zhihao Wu and Li Yixing and Xurui Zhou and Weiwen Liu and Shuai Wang and Kaiwen Zhou and Rui Shao and Liqiang Nie and Yasheng Wang and Jianye Hao and Jun Wang and Kun Shao},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2410.15164},
  url = {https://arxiv.org/abs/2410.15164}
}

@misc{arxiv241013886,
  title = {{Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents}},
  author = {Priyanshu Kumar and Elaine Lau and Saranya Vijayakumar and Tu Trinh and {Scale Red Team} and Elaine Chang and Vaughn Robinson and Sean Hendryx and Shuyan Zhou and Matt Fredrikson and Summer Yue and Zifan Wang},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2410.13886},
  url = {https://arxiv.org/abs/2410.13886}
}

@misc{arxiv241005080,
  title = {{ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery}},
  author = {Ziru Chen and Shijie Chen and Yuting Ning and Qianheng Zhang and Boshi Wang and Botao Yu and Yifei Li and Zeyi Liao and Chen Wei and Zitong Lu and Vishal Dey and Mingyi Xue and Frazier N. Baker and Benjamin Burns and Daniel Adu-Ampratwum and Xuhui Huang and Xia Ning and Song Gao and Yu Su and Huan Sun},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2410.05080},
  url = {https://arxiv.org/abs/2410.05080}
}

@misc{arxiv240908264,
  title = {{Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale}},
  author = {Rogerio Bonatti and Dan Zhao and Francesco Bonacci and Dillon Dupont and Sara Abdali and Yinheng Li and Yadong Lu and Justin Wagle and Kazuhito Koishida and Arthur Bucker and Lawrence Jang and Zack Hui},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2409.08264},
  url = {https://arxiv.org/abs/2409.08264}
}

@misc{arxiv240804682,
  title = {{ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities}},
  author = {Jiarui Lu and Thomas Holleis and Yizhe Zhang and Bernhard Aumayer and Feng Nan and Felix Bai and Shuang Ma and Shen Ma and Mengyu Li and Guoli Yin and Zirui Wang and Ruoming Pang},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2408.04682},
  url = {https://arxiv.org/abs/2408.04682}
}

@misc{arxiv240719056,
  title = {{OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation}},
  author = {Zilong Wang and Yuedong Cui and Li Zhong and Zimin Zhang and Da Yin and Bill Yuchen Lin and Jingbo Shang},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2407.19056},
  url = {https://arxiv.org/abs/2407.19056}
}

@misc{arxiv240718901,
  title = {{AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents}},
  author = {Harsh Trivedi and Tushar Khot and Mareike Hartmann and Ruskin Manku and Vinty Dong and Edward Li and Shashank Gupta and Ashish Sabharwal and Niranjan Balasubramanian},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2407.18901},
  url = {https://arxiv.org/abs/2407.18901}
}

@misc{arxiv240717032,
  title = {{Gymnasium: A Standard Interface for Reinforcement Learning Environments}},
  author = {Mark Towers and Ariel Kwiatkowski and Jordan Terry and John U. Balis and Gianluca De Cola and Tristan Deleu and Manuel Goulão and Andreas Kallinteris and Markus Krimmel and Arjun KG and Rodrigo Perez-Vicente and Andrea Pierré and Sander Schulhoff and Jun Jet Tai and Hannah Tan and Omar G. Younis},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2407.17032},
  url = {https://arxiv.org/abs/2407.17032}
}

@misc{arxiv240716312,
  title = {{MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning}},
  author = {Florian Felten and Umut Ucak and Hicham Azmani and Gao Peng and Willem Röpke and Hendrik Baier and Patrick Mannion and Diederik M. Roijers and Jordan K. Terry and El-Ghazali Talbi and Grégoire Danoy and Ann Nowé and Roxana Rădulescu},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2407.16312},
  url = {https://arxiv.org/abs/2407.16312}
}

@misc{arxiv240715711,
  title = {{AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?}},
  author = {Ori Yoran and Samuel Joseph Amouyal and Chaitanya Malaviya and Ben Bogin and Ofir Press and Jonathan Berant},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2407.15711},
  url = {https://arxiv.org/abs/2407.15711}
}

@misc{arxiv240710956,
  title = {{Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?}},
  author = {Ruisheng Cao and Fangyu Lei and Haoyuan Wu and Jixuan Chen and Yeqiao Fu and Hongcheng Gao and Xinzhuang Xiong and Hanchong Zhang and Yuchen Mao and Wenjing Hu and Tianbao Xie and Hongshen Xu and Danyang Zhang and Sida Wang and Ruoxi Sun and Pengcheng Yin and Caiming Xiong and Ansong Ni and Qian Liu and Victor Zhong and Lu Chen and Kai Yu and Tao Yu},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2407.10956},
  url = {https://arxiv.org/abs/2407.10956}
}

@misc{arxiv240717490,
  title = {{AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents}},
  author = {Yuxiang Chai and Siyuan Huang and Yazhe Niu and Han Xiao and Liang Liu and Dingyu Zhang and Shuai Ren and Hongsheng Li},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2407.17490},
  url = {https://arxiv.org/abs/2407.17490}
}

@misc{arxiv240614991,
  title = {{SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation}},
  author = {Zeyao Ma and Bohan Zhang and Jing Zhang and Jifan Yu and Xiaokang Zhang and Xiaohan Zhang and Sijia Luo and Xi Wang and Jie Tang},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2406.14991},
  url = {https://arxiv.org/abs/2406.14991}
}

@misc{arxiv240613352,
  title = {{AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents}},
  author = {Edoardo Debenedetti and Jie Zhang and Mislav Balunović and Luca Beurer-Kellner and Marc Fischer and Florian Tramèr},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2406.13352},
  url = {https://arxiv.org/abs/2406.13352}
}

@misc{arxiv240611317,
  title = {{GUICourse: From General Vision Language Models to Versatile GUI Agents}},
  author = {Wentong Chen and Junbo Cui and Jinyi Hu and Yujia Qin and Junjie Fang and Yue Zhao and Chongyi Wang and Jun Liu and Guirong Chen and Yupeng Huo and Yuan Yao and Yankai Lin and Zhiyuan Liu and Maosong Sun},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2406.11317},
  url = {https://arxiv.org/abs/2406.11317}
}

@misc{arxiv240610819,
  title = {{GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding}},
  author = {Dongping Chen and Yue Huang and Siyuan Wu and Jingyu Tang and Liuyi Chen and Yilin Bai and Zhigang He and Chenlong Wang and Huichi Zhou and Yiqiang Li and Tianshuo Zhou and Yue Yu and Chujie Gao and Qihui Zhang and Yi Gui and Zhen Li and Yao Wan and Pan Zhou and Jianfeng Gao and Lichao Sun},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2406.10819},
  url = {https://arxiv.org/abs/2406.10819}
}

@misc{arxiv240610227,
  title = {{VideoGUI: A Benchmark for GUI Automation from Instructional Videos}},
  author = {Kevin Qinghong Lin and Linjie Li and Difei Gao and Qinchen WU and Mingyi Yan and Zhengyuan Yang and Lijuan Wang and Mike Zheng Shou},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2406.10227},
  url = {https://arxiv.org/abs/2406.10227}
}

@misc{arxiv240608451,
  title = {{GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices}},
  author = {Quanfeng Lu and Wenqi Shao and Zitao Liu and Lingxiao Du and Fanqing Meng and Boxuan Li and Botong Chen and Siyuan Huang and Kaipeng Zhang and Ping Luo},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2406.08451},
  url = {https://arxiv.org/abs/2406.08451}
}

@misc{arxiv240608184,
  title = {{MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents}},
  author = {Luyuan Wang and Yongyu Deng and Yiwei Zha and Guodong Mao and Qinmin Wang and Tianchen Min and Wei Chen and Shoufa Chen},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2406.08184},
  url = {https://arxiv.org/abs/2406.08184}
}

@misc{arxiv240612905,
  title = {{PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice}},
  author = {Joseph Suarez},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2406.12905},
  url = {https://arxiv.org/abs/2406.12905}
}

@misc{arxiv240604151,
  title = {{AgentGym: Evolving Large Language Model-based Agents across Diverse Environments}},
  author = {Zhiheng Xi and Yiwen Ding and Wenxiang Chen and Boyang Hong and Honglin Guo and Junzhe Wang and Dingwen Yang and Chenyang Liao and Xin Guo and Wei He and Songyang Gao and Lu Chen and Rui Zheng and Yicheng Zou and Tao Gui and Qi Zhang and Xipeng Qiu and Xuanjing Huang and Zuxuan Wu and Yu-Gang Jiang},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2406.04151},
  url = {https://arxiv.org/abs/2406.04151}
}

@misc{arxiv240603679,
  title = {{On the Effects of Data Scale on UI Control Agents}},
  author = {Wei Li and William Bishop and Alice Li and Chris Rawles and Folawiyo Campbell-Ajala and Divya Tyamagundlu and Oriana Riva},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2406.03679},
  url = {https://arxiv.org/abs/2406.03679}
}

@misc{arxiv240514573,
  title = {{AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents}},
  author = {Christopher Rawles and Sarah Clinckemaillie and Yifan Chang and Jonathan Waltz and Gabrielle Lau and Marybeth Fair and Alice Li and William Bishop and Wei Li and Folawiyo Campbell-Ajala and Daniel Toyama and Robert Berry and Divya Tyamagundlu and Timothy Lillicrap and Oriana Riva},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2405.14573},
  url = {https://arxiv.org/abs/2405.14573}
}

@misc{arxiv240500823,
  title = {{WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting}},
  author = {Olly Styles and Sam Miller and Patricio Cerda-Mardini and Tanaya Guha and Victor Sanchez and Bertie Vidgen},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2405.00823},
  url = {https://arxiv.org/abs/2405.00823}
}

@misc{arxiv240416054,
  title = {{LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task Automation}},
  author = {Li Zhang and Shihe Wang and Xianqing Jia and Zhihan Zheng and Yunhe Yan and Longxi Gao and Yuanchun Li and Mengwei Xu},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2404.16054},
  url = {https://arxiv.org/abs/2404.16054}
}

@misc{arxiv240407972,
  title = {{OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments}},
  author = {Tianbao Xie and Danyang Zhang and Jixuan Chen and Xiaochuan Li and Siheng Zhao and Ruisheng Cao and Toh Jing Hua and Zhoujun Cheng and Dongchan Shin and Fangyu Lei and Yitao Liu and Yiheng Xu and Shuyan Zhou and Silvio Savarese and Caiming Xiong and Victor Zhong and Tao Yu},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2404.07972},
  url = {https://arxiv.org/abs/2404.07972}
}

@misc{arxiv240406369,
  title = {{WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs}},
  author = {Yi Gui and Zhen Li and Yao Wan and Yemin Shi and Hongyu Zhang and Yi Su and Bohua Chen and Dongping Chen and Siyuan Wu and Xing Zhou and Wenbin Jiang and Hai Jin and Xiangliang Zhang},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2404.06369},
  url = {https://arxiv.org/abs/2404.06369}
}

@misc{arxiv240405955,
  title = {{VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?}},
  author = {Junpeng Liu and Yifan Song and Bill Yuchen Lin and Wai Lam and Graham Neubig and Yuanzhi Li and Xiang Yue},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2404.05955},
  url = {https://arxiv.org/abs/2404.05955}
}

@misc{arxiv240307718,
  title = {{WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?}},
  author = {Alexandre Drouin and Maxime Gasse and Massimo Caccia and Issam H. Laradji and Manuel Del Verme and Tom Marty and Léo Boisvert and Megh Thakkar and Quentin Cappart and David Vazquez and Nicolas Chapados and Alexandre Lacoste},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2403.07718},
  url = {https://arxiv.org/abs/2403.07718}
}

@misc{arxiv240307714,
  title = {{StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models}},
  author = {Zhicheng Guo and Sijie Cheng and Hao Wang and Shihao Liang and Yujia Qin and Peng Li and Zhiyuan Liu and Maosong Sun and Yang Liu},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2403.07714},
  url = {https://arxiv.org/abs/2403.07714}
}

@misc{arxiv240303163,
  title = {{Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering}},
  author = {Chenglei Si and Yanzhe Zhang and Ryan Li and Zhengyuan Yang and Ruibo Liu and Diyi Yang},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2403.03163},
  url = {https://arxiv.org/abs/2403.03163}
}

@misc{arxiv240302713,
  title = {{Android in the Zoo: Chain-of-Action-Thought for GUI Agents}},
  author = {Jiwen Zhang and Jihao Wu and Yihua Teng and Minghui Liao and Nuo Xu and Xiao Xiao and Zhongyu Wei and Duyu Tang},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2403.02713},
  url = {https://arxiv.org/abs/2403.02713}
}

@misc{arxiv240217553,
  title = {{OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web}},
  author = {Raghav Kapoor and Yash Parag Butala and Melisa Russak and Jing Yu Koh and Kiran Kamble and Waseem Alshikh and Ruslan Salakhutdinov},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2402.17553},
  url = {https://arxiv.org/abs/2402.17553}
}

@misc{arxiv240216801,
  title = {{Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning}},
  author = {Michael Matthews and Michael Beukman and Benjamin Ellis and Mikayel Samvelyan and Matthew Jackson and Samuel Coward and Jakob Foerster},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2402.16801},
  url = {https://arxiv.org/abs/2402.16801}
}

@misc{arxiv240205930,
  title = {{WebLINX: Real-World Website Navigation with Multi-Turn Dialogue}},
  author = {Xing Han Lù and Zdeněk Kasner and Siva Reddy},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2402.05930},
  url = {https://arxiv.org/abs/2402.05930}
}

@misc{arxiv240113919,
  title = {{WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models}},
  author = {Hongliang He and Wenlin Yao and Kaixin Ma and Wenhao Yu and Yong Dai and Hongming Zhang and Zhenzhong Lan and Dong Yu},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2401.13919},
  url = {https://arxiv.org/abs/2401.13919}
}

@misc{arxiv240113649,
  title = {{VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks}},
  author = {Jing Yu Koh and Robert Lo and Lawrence Jang and Vikram Duvvur and Ming Chong Lim and Po-Yu Huang and Graham Neubig and Shuyan Zhou and Ruslan Salakhutdinov and Daniel Fried},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2401.13649},
  url = {https://arxiv.org/abs/2401.13649}
}

@misc{arxiv240113178,
  title = {{AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents}},
  author = {Chang Ma and Junlei Zhang and Zhihao Zhu and Cheng Yang and Yujiu Yang and Yaohui Jin and Zhenzhong Lan and Lingpeng Kong and Junxian He},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2401.13178},
  url = {https://arxiv.org/abs/2401.13178}
}

@misc{arxiv240110935,
  title = {{SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents}},
  author = {Kanzhi Cheng and Qiushi Sun and Yougang Chu and Fangzhi Xu and Yantao Li and Jianbing Zhang and Zhiyong Wu},
  year = {2024},
  archivePrefix = {arXiv},
  eprint = {2401.10935},
  url = {https://arxiv.org/abs/2401.10935}
}

@misc{arxiv231212044,
  title = {{XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX}},
  author = {Alexander Nikulin and Vladislav Kurenkov and Ilya Zisman and Artem Agarkov and Viacheslav Sinii and Sergey Kolesnikov},
  year = {2023},
  archivePrefix = {arXiv},
  eprint = {2312.12044},
  url = {https://arxiv.org/abs/2312.12044}
}

@misc{arxiv231112983,
  title = {{GAIA: a benchmark for General AI Assistants}},
  author = {Grégoire Mialon and Clémentine Fourrier and Craig Swift and Thomas Wolf and Yann LeCun and Thomas Scialom},
  year = {2023},
  archivePrefix = {arXiv},
  eprint = {2311.12983},
  url = {https://arxiv.org/abs/2311.12983}
}

@misc{arxiv231006770,
  title = {{SWE-bench: Can Language Models Resolve Real-World GitHub Issues?}},
  author = {Carlos E. Jimenez and John Yang and Alexander Wettig and Shunyu Yao and Kexin Pei and Ofir Press and Karthik Narasimhan},
  year = {2023},
  archivePrefix = {arXiv},
  eprint = {2310.06770},
  url = {https://arxiv.org/abs/2310.06770}
}

@misc{arxiv230803688,
  title = {{AgentBench: Evaluating LLMs as Agents}},
  author = {Xiao Liu and Hao Yu and Hanchen Zhang and Yifan Xu and Xuanyu Lei and Hanyu Lai and Yu Gu and Hangliang Ding and Kaiwen Men and Kejuan Yang and Shudan Zhang and Xiang Deng and Aohan Zeng and Zhengxiao Du and Chenhui Zhang and Sheng Shen and Tianjun Zhang and Yu Su and Huan Sun and Minlie Huang and Yuxiao Dong and Jie Tang},
  year = {2023},
  archivePrefix = {arXiv},
  eprint = {2308.03688},
  url = {https://arxiv.org/abs/2308.03688}
}

@misc{arxiv230713854,
  title = {{WebArena: A Realistic Web Environment for Building Autonomous Agents}},
  author = {Shuyan Zhou and Frank F. Xu and Hao Zhu and Xuhui Zhou and Robert Lo and Abishek Sridhar and Xianyi Cheng and Tianyue Ou and Yonatan Bisk and Daniel Fried and Uri Alon and Graham Neubig},
  year = {2023},
  archivePrefix = {arXiv},
  eprint = {2307.13854},
  url = {https://arxiv.org/abs/2307.13854}
}

@misc{arxiv230710088,
  title = {{Android in the Wild: A Large-Scale Dataset for Android Device Control}},
  author = {Christopher Rawles and Alice Li and Daniel Rodriguez and Oriana Riva and Timothy Lillicrap},
  year = {2023},
  archivePrefix = {arXiv},
  eprint = {2307.10088},
  url = {https://arxiv.org/abs/2307.10088}
}

@misc{arxiv230614898,
  title = {{InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback}},
  author = {John Yang and Akshara Prabhakar and Karthik Narasimhan and Shunyu Yao},
  year = {2023},
  archivePrefix = {arXiv},
  eprint = {2306.14898},
  url = {https://arxiv.org/abs/2306.14898}
}

@misc{arxiv230613831,
  title = {{Minigrid \& Miniworld: Modular \& Customizable Reinforcement Learning Environments for Goal-Oriented Tasks}},
  author = {Maxime Chevalier-Boisvert and Bolun Dai and Mark Towers and Rodrigo de Lazcano and Lucas Willems and Salem Lahlou and Suman Pal and Pablo Samuel Castro and Jordan Terry},
  year = {2023},
  archivePrefix = {arXiv},
  eprint = {2306.13831},
  url = {https://arxiv.org/abs/2306.13831}
}

@misc{arxiv230609884,
  title = {{Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX}},
  author = {Clément Bonnet and Daniel Luo and Donal Byrne and Shikha Surana and Sasha Abramowitz and Paul Duckworth and Vincent Coyette and Laurence I. Midgley and Elshadai Tegegn and Tristan Kalloniatis and Omayma Mahjoub and Matthew Macfarlane and Andries P. Smit and Nathan Grinsztajn and Raphael Boige and Cemlyn N. Waters and Mohamed A. Mimouni and Ulrich A. Mbou Sob and Ruan de Kock and Siddarth Singh and Daniel Furelos-Blanco and Victor Le and Arnu Pretorius and Alexandre Laterre},
  year = {2023},
  archivePrefix = {arXiv},
  eprint = {2306.09884},
  url = {https://arxiv.org/abs/2306.09884}
}

@misc{arxiv230606070,
  title = {{Mind2Web: Towards a Generalist Agent for the Web}},
  author = {Xiang Deng and Yu Gu and Boyuan Zheng and Shijie Chen and Samuel Stevens and Boshi Wang and Huan Sun and Yu Su},
  year = {2023},
  archivePrefix = {arXiv},
  eprint = {2306.06070},
  url = {https://arxiv.org/abs/2306.06070}
}

@misc{arxiv230408244,
  title = {{API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs}},
  author = {Minghao Li and Yingxiu Zhao and Bowen Yu and Feifan Song and Hangyu Li and Haiyang Yu and Zhoujun Li and Fei Huang and Yongbin Li},
  year = {2023},
  archivePrefix = {arXiv},
  eprint = {2304.08244},
  url = {https://arxiv.org/abs/2304.08244}
}

@misc{arxiv221113746,
  title = {{Melting Pot 2.0}},
  author = {John P. Agapiou and Alexander Sasha Vezhnevets and Edgar A. Duéñez-Guzmán and Jayd Matyas and Yiran Mao and Peter Sunehag and Raphael Köster and Udari Madhushani and Kavya Kopparapu and Ramona Comanescu and DJ Strouse and Michael B. Johanson and Sukhdeep Singh and Julia Haas and Igor Mordatch and Dean Mobbs and Joel Z. Leibo},
  year = {2022},
  archivePrefix = {arXiv},
  eprint = {2211.13746},
  url = {https://arxiv.org/abs/2211.13746}
}

@misc{arxiv221111501,
  title = {{DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation}},
  author = {Yuhang Lai and Chengxi Li and Yiming Wang and Tianyi Zhang and Ruiqi Zhong and Luke Zettlemoyer and Scott Wen-tau Yih and Daniel Fried and Sida Wang and Tao Yu},
  year = {2022},
  archivePrefix = {arXiv},
  eprint = {2211.11501},
  url = {https://arxiv.org/abs/2211.11501}
}

@misc{arxiv220701206,
  title = {{WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents}},
  author = {Shunyu Yao and Howard Chen and John Yang and Karthik Narasimhan},
  year = {2022},
  archivePrefix = {arXiv},
  eprint = {2207.01206},
  url = {https://arxiv.org/abs/2207.01206}
}

@misc{arxiv220608853,
  title = {{MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge}},
  author = {Linxi Fan and Guanzhi Wang and Yunfan Jiang and Ajay Mandlekar and Yuncong Yang and Haoyi Zhu and Andrew Tang and De-An Huang and Yuke Zhu and Anima Anandkumar},
  year = {2022},
  archivePrefix = {arXiv},
  eprint = {2206.08853},
  url = {https://arxiv.org/abs/2206.08853}
}

@misc{arxiv220307540,
  title = {{ScienceWorld: Is your Agent Smarter than a 5th Grader?}},
  author = {Ruoyao Wang and Peter Jansen and Marc-Alexandre Côté and Prithviraj Ammanabrolu},
  year = {2022},
  archivePrefix = {arXiv},
  eprint = {2203.07540},
  url = {https://arxiv.org/abs/2203.07540}
}

@misc{arxiv210913202,
  title = {{MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research}},
  author = {Mikayel Samvelyan and Robert Kirk and Vitaly Kurin and Jack Parker-Holder and Minqi Jiang and Eric Hambro and Fabio Petroni and Heinrich Küttler and Edward Grefenstette and Tim Rocktäschel},
  year = {2021},
  archivePrefix = {arXiv},
  eprint = {2109.13202},
  url = {https://arxiv.org/abs/2109.13202}
}

@misc{arxiv210906780,
  title = {{Benchmarking the Spectrum of Agent Capabilities}},
  author = {Danijar Hafner},
  year = {2021},
  archivePrefix = {arXiv},
  eprint = {2109.06780},
  url = {https://arxiv.org/abs/2109.06780}
}

@misc{arxiv210706857,
  title = {{Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot}},
  author = {Joel Z. Leibo and Edgar Duéñez-Guzmán and Alexander Sasha Vezhnevets and John P. Agapiou and Peter Sunehag and Raphael Koster and Jayd Matyas and Charles Beattie and Igor Mordatch and Thore Graepel},
  year = {2021},
  archivePrefix = {arXiv},
  eprint = {2107.06857},
  url = {https://arxiv.org/abs/2107.06857}
}

@misc{arxiv210513231,
  title = {{AndroidEnv: A Reinforcement Learning Platform for Android}},
  author = {Daniel Toyama and Philippe Hamel and Anita Gergely and Gheorghe Comanici and Amelia Glaese and Zafarali Ahmed and Tyler Jackson and Shibl Mourad and Doina Precup},
  year = {2021},
  archivePrefix = {arXiv},
  eprint = {2105.13231},
  url = {https://arxiv.org/abs/2105.13231}
}

@misc{arxiv201107027,
  title = {{DeepMind Lab2D}},
  author = {Charles Beattie and Thomas Köppe and Edgar A. Duéñez-Guzmán and Joel Z. Leibo},
  year = {2020},
  archivePrefix = {arXiv},
  eprint = {2011.07027},
  url = {https://arxiv.org/abs/2011.07027}
}

@misc{arxiv201106363,
  title = {{Griddly: A platform for AI research in games}},
  author = {Chris Bamford and Shengyi Huang and Simon Lucas},
  year = {2020},
  archivePrefix = {arXiv},
  eprint = {2011.06363},
  url = {https://arxiv.org/abs/2011.06363}
}

@misc{arxiv201003768,
  title = {{ALFWorld: Aligning Text and Embodied Environments for Interactive Learning}},
  author = {Mohit Shridhar and Xingdi Yuan and Marc-Alexandre Côté and Yonatan Bisk and Adam Trischler and Matthew Hausknecht},
  year = {2020},
  archivePrefix = {arXiv},
  eprint = {2010.03768},
  url = {https://arxiv.org/abs/2010.03768}
}

@misc{arxiv200914471,
  title = {{PettingZoo: Gym for Multi-Agent Reinforcement Learning}},
  author = {J. K. Terry and Benjamin Black and Nathaniel Grammel and Mario Jayakumar and Ananth Hari and Ryan Sullivan and Luis Santos and Rodrigo Perez and Caroline Horsch and Clemens Dieffendahl and Niall L. Williams and Yashas Lokesh and Praveen Ravi},
  year = {2020},
  archivePrefix = {arXiv},
  eprint = {2009.14471},
  url = {https://arxiv.org/abs/2009.14471}
}

@misc{arxiv200613760,
  title = {{The NetHack Learning Environment}},
  author = {Heinrich Küttler and Nantas Nardelli and Alexander H. Miller and Roberta Raileanu and Marco Selvatici and Edward Grefenstette and Tim Rocktäschel},
  year = {2020},
  archivePrefix = {arXiv},
  eprint = {2006.13760},
  url = {https://arxiv.org/abs/2006.13760}
}

@misc{arxiv191201588,
  title = {{Leveraging Procedural Generation to Benchmark Reinforcement Learning}},
  author = {Karl Cobbe and Christopher Hesse and Jacob Hilton and John Schulman},
  year = {2019},
  archivePrefix = {arXiv},
  eprint = {1912.01588},
  url = {https://arxiv.org/abs/1912.01588}
}

@misc{arxiv191004376,
  title = {{RLCard: A Toolkit for Reinforcement Learning in Card Games}},
  author = {Daochen Zha and Kwei-Herng Lai and Yuanpu Cao and Songyi Huang and Ruzhe Wei and Junyu Guo and Xia Hu},
  year = {2019},
  archivePrefix = {arXiv},
  eprint = {1910.04376},
  url = {https://arxiv.org/abs/1910.04376}
}

@misc{arxiv190905398,
  title = {{Interactive Fiction Games: A Colossal Adventure}},
  author = {Matthew Hausknecht and Prithviraj Ammanabrolu and Marc-Alexandre Côté and Xingdi Yuan},
  year = {2019},
  archivePrefix = {arXiv},
  eprint = {1909.05398},
  url = {https://arxiv.org/abs/1909.05398}
}

@misc{arxiv190809453,
  title = {{OpenSpiel: A Framework for Reinforcement Learning in Games}},
  author = {Marc Lanctot and Edward Lockhart and Jean-Baptiste Lespiau and Vinicius Zambaldi and Satyaki Upadhyay and Julien Pérolat and Sriram Srinivasan and Finbarr Timbers and Karl Tuyls and Shayegan Omidshafiei and Daniel Hennes and Dustin Morrill and Paul Muller and Timo Ewalds and Ryan Faulkner and János Kramár and Bart De Vylder and Brennan Saeta and James Bradbury and David Ding and Sebastian Borgeaud and Matthew Lai and Julian Schrittwieser and Thomas Anthony and Edward Hughes and Ivo Danihelka and Jonah Ryan-Davis},
  year = {2019},
  archivePrefix = {arXiv},
  eprint = {1908.09453},
  url = {https://arxiv.org/abs/1908.09453}
}

@misc{arxiv190803568,
  title = {{Behaviour Suite for Reinforcement Learning}},
  author = {Ian Osband and Yotam Doron and Matteo Hessel and John Aslanides and Eren Sezener and Andre Saraiva and Katrina McKinney and Tor Lattimore and Csaba Szepesvari and Satinder Singh and Benjamin Van Roy and Richard Sutton and David Silver and Hado Van Hasselt},
  year = {2019},
  archivePrefix = {arXiv},
  eprint = {1908.03568},
  url = {https://arxiv.org/abs/1908.03568}
}

@misc{arxiv190713440,
  title = {{MineRL: A Large-Scale Dataset of Minecraft Demonstrations}},
  author = {William H. Guss and Brandon Houghton and Nicholay Topin and Phillip Wang and Cayden Codel and Manuela Veloso and Ruslan Salakhutdinov},
  year = {2019},
  archivePrefix = {arXiv},
  eprint = {1907.13440},
  url = {https://arxiv.org/abs/1907.13440}
}

@misc{arxiv180903470,
  title = {{ViZDoom Competitions: Playing Doom from Pixels}},
  author = {Marek Wydmuch and Michał Kempka and Wojciech Jaśkowski},
  year = {2018},
  archivePrefix = {arXiv},
  eprint = {1809.03470},
  url = {https://arxiv.org/abs/1809.03470}
}

@misc{arxiv180902627,
  title = {{Unity: A General Platform for Intelligent Agents}},
  author = {Arthur Juliani and Vincent-Pierre Berges and Ervin Teng and Andrew Cohen and Jonathan Harper and Chris Elion and Chris Goy and Yuan Gao and Hunter Henry and Marwan Mattar and Danny Lange},
  year = {2018},
  archivePrefix = {arXiv},
  eprint = {1809.02627},
  url = {https://arxiv.org/abs/1809.02627}
}

@misc{arxiv180611532,
  title = {{TextWorld: A Learning Environment for Text-based Games}},
  author = {Marc-Alexandre Côté and Ákos Kádár and Xingdi Yuan and Ben Kybartas and Tavian Barnes and Emery Fine and James Moore and Ruo Yu Tao and Matthew Hausknecht and Layla El Asri and Mahmoud Adada and Wendy Tay and Adam Trischler},
  year = {2018},
  archivePrefix = {arXiv},
  eprint = {1806.11532},
  url = {https://arxiv.org/abs/1806.11532}
}

@misc{arxiv180607011,
  title = {{VirtualHome: Simulating Household Activities via Programs}},
  author = {Xavier Puig and Kevin Ra and Marko Boben and Jiaman Li and Tingwu Wang and Sanja Fidler and Antonio Torralba},
  year = {2018},
  archivePrefix = {arXiv},
  eprint = {1806.07011},
  url = {https://arxiv.org/abs/1806.07011}
}

@misc{arxiv180210363,
  title = {{General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithms}},
  author = {Diego Perez-Liebana and Jialin Liu and Ahmed Khalifa and Raluca D. Gaina and Julian Togelius and Simon M. Lucas},
  year = {2018},
  archivePrefix = {arXiv},
  eprint = {1802.10363},
  url = {https://arxiv.org/abs/1802.10363}
}

@misc{arxiv180208802,
  title = {{Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration}},
  author = {Evan Zheran Liu and Kelvin Guu and Panupong Pasupat and Tianlin Shi and Percy Liang},
  year = {2018},
  archivePrefix = {arXiv},
  eprint = {1802.08802},
  url = {https://arxiv.org/abs/1802.08802}
}

@misc{arxiv171200600,
  title = {{MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence}},
  author = {Lianmin Zheng and Jiacheng Yang and Han Cai and Weinan Zhang and Jun Wang and Yong Yu},
  year = {2017},
  archivePrefix = {arXiv},
  eprint = {1712.00600},
  url = {https://arxiv.org/abs/1712.00600}
}

@misc{arxiv170602275,
  title = {{Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments}},
  author = {Ryan Lowe and Yi Wu and Aviv Tamar and Jean Harb and Pieter Abbeel and Igor Mordatch},
  year = {2017},
  archivePrefix = {arXiv},
  eprint = {1706.02275},
  url = {https://arxiv.org/abs/1706.02275}
}

@misc{arxiv170304908,
  title = {{Emergence of Grounded Compositional Language in Multi-Agent Populations}},
  author = {Igor Mordatch and Pieter Abbeel},
  year = {2017},
  archivePrefix = {arXiv},
  eprint = {1703.04908},
  url = {https://arxiv.org/abs/1703.04908}
}

@misc{arxiv161203801,
  title = {{DeepMind Lab}},
  author = {Charles Beattie and Joel Z. Leibo and Denis Teplyashin and Tom Ward and Marcus Wainwright and Heinrich Küttler and Andrew Lefrancq and Simon Green and Víctor Valdés and Amir Sadik and Julian Schrittwieser and Keith Anderson and Sarah York and Max Cant and Adam Cain and Adrian Bolton and Stephen Gaffney and Helen King and Demis Hassabis and Shane Legg and Stig Petersen},
  year = {2016},
  archivePrefix = {arXiv},
  eprint = {1612.03801},
  url = {https://arxiv.org/abs/1612.03801}
}

@misc{arxiv160502097,
  title = {{ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning}},
  author = {Michał Kempka and Marek Wydmuch and Grzegorz Runc and Jakub Toczek and Wojciech Jaśkowski},
  year = {2016},
  archivePrefix = {arXiv},
  eprint = {1605.02097},
  url = {https://arxiv.org/abs/1605.02097}
}

@misc{arxiv12074708,
  title = {{The Arcade Learning Environment: An Evaluation Platform for General Agents}},
  author = {Marc G. Bellemare and Yavar Naddaf and Joel Veness and Michael Bowling},
  year = {2012},
  archivePrefix = {arXiv},
  eprint = {1207.4708},
  url = {https://arxiv.org/abs/1207.4708}
}