Conference paper · 2026

Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation

Sayash Kapoor, Benedikt Stroebl, Peter Kirgis, Nitya Nadgir, Zachary S. Siegel, Boyi Wei, Tianci Xue, Ziru Chen, Felix Chen, Saiteja Utpala, Franck Ndzomga, Dheeraj Oruganty, Sophie Luskin, Kangheng Liu, Botao Yu, Amit Arora, Dongyoon Hahm, Harsh Trivedi, Huan Sun, Juyong Lee, Tengjun Jin, Yifan Mai, Yifei Zhou, Yuxuan Zhu, Rishi Bommasani, Daniel Kang, Dawn Song, Peter Henderson, Yu Su, Percy Liang, Arvind Narayanan

BibTeX Copy

@inproceedings{kapoor2026hal,
	title = {Holistic {Agent} {Leaderboard}: {The} {Missing} {Infrastructure} for {AI} {Agent} {Evaluation}},
	url = {https://arxiv.org/abs/2510.11977},
	booktitle = {International {Conference} on {Learning} {Representations} ({ICLR})},
	author = {Kapoor, Sayash and Stroebl, Benedikt and Kirgis, Peter and Nadgir, Nitya and Siegel, Zachary S. and Wei, Boyi and Xue, Tianci and Chen, Ziru and Chen, Felix and Utpala, Saiteja and Ndzomga, Franck and Oruganty, Dheeraj and Luskin, Sophie and Liu, Kangheng and Yu, Botao and Arora, Amit and Hahm, Dongyoon and Trivedi, Harsh and Sun, Huan and Lee, Juyong and Jin, Tengjun and Mai, Yifan and Zhou, Yifei and Zhu, Yuxuan and Bommasani, Rishi and Kang, Daniel and Song, Dawn and Henderson, Peter and Su, Yu and Liang, Percy and Narayanan, Arvind},
	year = {2026},
	note = {arXiv: 2510.11977},
	keywords = {replichai},
}