一作ICML 2026Poster
FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights
Zhen Wang · Fan Bai · Zhongyan Luo · Jinyan Su · Kaiser Sun · Xinle Yu · Jieyuan Liu · Kun Zhou · Claire Cardie · Mark Dredze · Zhiting Hu · Eric Xing
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Zhen Wang · Fan Bai · Zhongyan Luo · Jinyan Su · Kaiser Sun · Xinle Yu · Jieyuan Liu · Kun Zhou · Claire Cardie · Mark Dredze · Zhiting Hu · Eric Xing
Yanbin Yin · Kun Zhou · Zhen Wang · Xiangdong Zhang · Yifei Shao · Shibo Hao · Yi Gu · Jieyuan Liu · Somanshu Singla · Tianyang Liu · Eric P. Xing · Zhengzhong Liu · Haojian Jin · Zhiting Hu
The recent explosion of large language models (LLMs), each with its own general or specialized strengths, makes scalable, reliable benchmarking more urgent than ever. Standard practices nowadays face fundamental trade-offs: closed-ended question-based benchmarks (MMLU) struggle with saturation as...