DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent.

@inproceedings{wu-2026-deepresearch9k, author = {Tongzhou Wu and Gordon V. Cormack and Xinyu Ma and Dawei Yin and Juli\'{a}n Urbano and Yuhao Wang and Maura R. Grossman and Xiuqiang He and Gordon V. Cormack and Xinyu Ma and Chris Buckley and Xiangyu Zhao and Maura R. Grossman and Xiuqiang He and Shuaiqiang Wang and Dawei Yin and Juli\'{a}n Urbano and Chris Buckley and Xiangyu Zhao}, editor = {Hannah Bast and Alistair Moffat and Falk Scholer and Marc Najork and Min Zhang and Hannah Bast and Marc Najork and Min Zhang}, title = {{DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent}}, booktitle = {{Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026}}, pages = {3481--3488}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3808597}, doi = {https://doi.org/10.1145/3805712.3808597} }