QuarkMedSearch: A Long-Horizon Deep Search Agent for Exploring Medical Intelligence

TL;DR

QuarkMedSearch is a novel deep search agent tailored for Chinese medical intelligence, utilizing a comprehensive pipeline of data synthesis, training, and evaluation to achieve state-of-the-art results.

Contribution

It introduces a full-pipeline approach including data construction, two-stage training, and expert-verified benchmarks for medical deep search.

Findings

Achieves state-of-the-art performance on QuarkMedSearch Benchmark.

Effectively combines knowledge graph and online exploration for data synthesis.

Enhances model capabilities with a two-stage training strategy.

Abstract

As agentic foundation models continue to evolve, how to further improve their performance in vertical domains has become an important challenge. To this end, building upon Tongyi DeepResearch, a powerful agentic foundation model, we focus on the Chinese medical deep search scenario and propose QuarkMedSearch, systematically exploring a full-pipeline approach spanning medical multi-hop data construction, training strategies, and evaluation benchmarks to further push and assess its performance upper bound in vertical domains. Specifically, for data synthesis, to address the scarcity of deep search training data in the medical domain, we combine a large-scale medical knowledge graph with real-time online exploration to construct long-horizon medical deep search training data; for post-training, we adopt a two-stage SFT and RL training strategy that progressively enhances the model's planning, tool invocation, and reflection capabilities required for deep search, while maintaining search efficiency; for evaluation, we collaborate with medical experts to construct the QuarkMedSearch Benchmark through rigorous manual verification. Experimental results demonstrate that QuarkMedSearch achieves state-of-the-art performance among open-source models of comparable scale on the QuarkMedSearch Benchmark, while also maintaining strong competitiveness on general benchmarks.