Artificial intelligence systems for scientific discovery have demonstrated remarkable potential, yet existing approaches remain largely proprietary and operate in batch-processing modes requiring hours per research cycle, precluding real-time researcher guidance. This paper introduces Deep Research, a multi-agent system enabling interactive scientific investigation with turnaround times measured in minutes. The architecture comprises specialized agents for planning, data analysis, literature search, and novelty detection, unified through a persistent world state that maintains context across iterative research cycles. Two operational modes support different workflows: semi-autonomous mode with selective human checkpoints, and fully autonomous mode for extended investigations. Evaluation on the BixBench computational biology benchmark demonstrated state-of-the-art performance, achieving 48.8% accuracy on open response and 64.4% on multiple-choice evaluation, exceeding existing baselines by 14 to 26 percentage points. Analysis of architectural constraints, including open access literature limitations and challenges inherent to automated novelty assessment, informs practical deployment considerations for AI-assisted scientific workflows.

翻译：科学发现人工智能系统已展现出显著潜力，但现有方法仍主要采用专有架构并以批处理模式运行，每个研究周期需耗时数小时，无法实现研究人员的实时指导。本文提出Deep Research多智能体系统，该系统支持分钟级响应的交互式科学研究。该架构包含规划、数据分析、文献检索和新颖性检测等专用智能体，通过持久化世界状态进行统一协调，在迭代研究周期中保持上下文连贯性。系统提供两种运行模式以支持不同工作流：包含选择性人工检查点的半自主模式，以及适用于长期探索的全自主模式。在BixBench计算生物学基准测试中的评估表明，系统在开放回答任务上达到48.8%准确率，多项选择任务上达到64.4%准确率，较现有基线提升14至26个百分点，实现了最先进的性能表现。通过对架构约束（包括开放获取文献的局限性及自动化新颖性评估的固有挑战）的分析，为人工智能辅助科学工作流的实际部署提供了实践指导。