SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning
For AI researchers aiming to build automated scientific discovery agents, SciResearcher provides a scalable data construction paradigm that overcomes the limitations of existing methods in sparse, heterogeneous scientific domains.
SciResearcher introduces a fully automated framework for constructing training data in frontier scientific domains, enabling an 8B-parameter agent to achieve 19.46% on HLE-Bio/Chem-Gold (SOTA at its scale) and 13-15% absolute gains on other benchmarks, surpassing larger proprietary agents.
Frontier scientific reasoning is rapidly emerging as a key foundation for advancing AI agents in automated scientific discovery. Deep research agents offer a promising approach to this challenge. These models develop robust problem-solving capabilities through post-training on information-seeking tasks, which are typically curated via knowledge graph construction or iterative web browsing. However, these strategies face inherent limitations in frontier science, where domain-specific knowledge is scattered across sparse and heterogeneous academic sources, and problem solving requires sophisticated computation and reasoning far beyond factual recall. To bridge this gap, we introduce SciResearcher, a fully automated agentic framework for frontier-science data construction. SciResearcher synthesizes diverse conceptual and computational tasks grounded in academic evidence, while eliciting information acquisition, tool-integrated reasoning, and long-horizon capabilities. Leveraging the curated data for supervised fine-tuning and agentic reinforcement learning, we develop SciResearcher-8B, an agent foundation model that achieves 19.46% on the HLE-Bio/Chem-Gold benchmark, establishing a new state of the art at its parameter scale and surpassing several larger proprietary agents. It further achieves 13-15% absolute gains on SuperGPQA-Hard-Biology and TRQA-Literature benchmarks. Overall, SciResearcher introduces a new paradigm for automated data construction for frontier scientific reasoning and offers a scalable path toward future scientific agents.