arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.05985cs.AIcs.MAq-bio.QM
收藏

BioResearcher: 用于转化医学的场景引导多智能体系统

BioResearcher: Scenario-Guided Multi-Agent for Translational Medicine

Remigiusz Kinas, Joanna Krawczyk, Rafał Powalski, Przemysław Pietrzak, Agnieszka Kowalewska, Krzysztof Kolmus, Maciej Sypetkowski, Łukasz Smoliński, Tomasz Jetka

AI总结:

本文提出BioResearcher,一种场景引导的多智能体系统,通过版本化研究 playbook 将查询映射到多种工具和机器学习端点,实现跨异构生物医学数据源的可审计、场景特定工作流。系统在单元级能力、开放性生物医学推理和端到端临床发现中均表现优异。

摘要:

转化医学将模糊的开发目标转化为需要结合文献、试验、专利和定量多组学分析的证据综合,同时需保持标识符、不确定性和可追溯的来源。通用基础模型和现成工具增强或多智能体系统不适用于此:它们倾向于产生单次回答或运行开放性,无法满足异构生物医学数据源所需的可审计、场景特定的工作流。本文介绍Ingenix BioResearcher,一种场景引导的多智能体系统,将查询映射到版本化研究playbook,委托给超过30种工具和机器学习端点的专门子智能体,结合结构化数据库访问与沙盒代码进行基因组级分析,并在编辑前应用基于声明的多模型 reconciliation。我们评估了BioResearcher在单元级能力、开放性生物医学推理和端到端临床发现中的表现。它在109个单步测试中优于评估基线(83.49%通过率;0.892平均分),在生物医学基准测试(BixBench-Verified-50上89.33%和BaisBench Scientific Discovery上0.758均分)中表现强劲,并在30个查询的端到端临床基准测试中领先,最高正向命中率(74.7%±3.3%)和负向清晰率(96.8%±0.2%)。这些结果表明,系统在单元级、开放性和端到端临床评估中均表现出广泛且具有竞争力的性能。

英文摘要:

Translational medicine turns underspecified development goals into evidence synthesis that must combine literature, trials, patents, and quantitative multi-omics analysis while preserving identifiers, uncertainty, and retrievable provenance. General-purpose foundation models and off-the-shelf tool-augmented or multi-agent systems are not built for this: they tend to produce single-shot answers or run open-endedly, and fall short on the auditable, scenario-specific workflows that heterogeneous biomedical sources demand. This paper introduces Ingenix BioResearcher, a scenario-guided multi-agent system that maps queries to versioned research playbooks, delegates to specialized subagents over 30+ tools and machine-learning endpoints, mixes structured database access with sandboxed code for genome-scale analyses, and applies claim-level multi-model reconciliation before editorial assembly. We evaluate BioResearcher across unit-level capabilities, open-ended biomedical reasoning, and end-to-end clinical discovery. It leads evaluated baselines on 109 single-step tests (83.49% pass rate; 0.892 average score), achieves strong biomedical benchmark performance (89.33% on BixBench-Verified-50 and the top 0.758 mean score on BaisBench Scientific Discovery), and leads on a 30-query clinical end-to-end benchmark with the highest positive hit rate (74.7% $\pm$ 3.3%) and negative clear rate (96.8% $\pm$ 0.2%). These results show broad, competitive performance across unit-level, open-ended, and end-to-end clinical evaluations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑