F$^{2}$DR: A Fine-Grained Full-Pipeline Reward Framework for DeepSearch Workflows
F2DR evaluates DeepSearch workflows across three dimensions: Content, Trajectory, and Answer, enabling comprehensive process-level assessment, and constructs DeepSearch RM-Bench, a dedicated benchmark for evaluating RMs in DeepSearch scenarios.
Bo-Jian Xiong, Wen-Tao Ding, Yu-Jing Lu et al.
· 0 citations