Conference paper · 2026
FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights
| Venue | Proceedings of the 43rd International Conference on Machine Learning |
|---|---|
| URL | https://arxiv.org/abs/2602.02905 |
| Topics | ReplicHAI / Agentic reproduction: systems & benchmarks |
| Tags | replichai |
| citationKey | wang2026firebench |
| conferenceName | Proceedings of Machine Learning Research |
| extra | arXiv: 2602.02905 Note: PMLR pages not verified |
| libraryCatalog | background/agentic-systems/refs.bib |
| volume | 306 |
BibTeX
@inproceedings{wang2026firebench,
title = {{FIRE}-{Bench}: {Evaluating} {AI} {Agents} on the {Rediscovery} of {Scientific} {Insights}},
volume = {306},
url = {https://arxiv.org/abs/2602.02905},
booktitle = {Proceedings of the 43rd {International} {Conference} on {Machine} {Learning}},
author = {Wang, Zhen and Bai, Fan and Luo, Zhongyan and Su, Jinyan and Sun, Kaiser and Yu, Xinle and Liu, Jieyuan and Zhou, Kun and Cardie, Claire and Dredze, Mark and Hu, Zhiting and Xing, Eric P.},
year = {2026},
note = {arXiv: 2602.02905
Note: PMLR pages not verified},
keywords = {replichai},
}