Inspire: Benchmarking Scientific Literature Search for Open Research Problems
INSPIRE, a benchmark for evaluating agents that search prior literature to make progress on solution-redacted research problems, enables both end-to-end comparison and stage-resolved diagnosis in a setting where the agent must construct its own working criterion of relevance.
Jian-Rong Ding, Zheng-Yan Shi, Jian-Yuan Zhong et al.
· 0 citations