F$^{2}$DR: A Fine-Grained Full-Pipeline Reward Framework for DeepSearch Workflows

Excerpt

arXiv:2609.19827v1 Announce Type: new Abstract: With the widespread industrial deployment of Large Language Models (LLMs), DeepSearch has emerged as the dominant paradigm for resolving complex user queries. It typically operates through an iterative closed-loop workflow consisting of planning and reflection, information retrieval, and answer generation. However, existing reward models (RMs) and evaluation benchmarks are primarily designed for static single-turn tasks, failing to capture the full