SciForge：用于科学发现的人工智能原生多模态工作台
SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery
- Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
SciForge针对科学工作中异构工件难保存为连贯可审计状态的问题，构建多模态工作台，围绕五个支柱运行，结合多种组件，通过多种应用场景展示实际影响，当前为桌面应用，未来深化团队协作且开源。
AI中文摘要：
科学工作越来越多地涉及异构工件，如论文、代码、数据集等，但通用人工智能助手很少能将这些对象保留为连贯、可审计的研究状态。我们提出了SciForge，这是一个多模态研究原生人工智能工作台，其保留图形界面供人类判断，而搜索、解析、模型路由、工作流执行、绘图、写作和演示生成等作为模块化的可通过代理访问的服务运行。SciForge围绕五个支柱构建：目标范围科学决策治理、先翻译后推理、证据治理、协作团队科学、实际应用场景。该系统结合了薄交互层、上下文研究能力模式、代理运行时和工作流引擎、证据DAG审计边车和科学模型路由器。目前作为桌面应用运行，未来版本将深化团队协作，且系统开源。
英文摘要：
Scientific work increasingly spans heterogeneous artifacts -- papers, code, datasets, scientific file formats, model outputs, figures, manuscripts, and team decisions -- yet general-purpose AI assistants rarely preserve these objects as a coherent, auditable research state. We present SciForge, a multimodal research-native AI workbench that reserves the graphical interface for human judgment while search, parsing, model routing, workflow execution, plotting, writing, and presentation generation run as modular agent-accessible services. SciForge is built around five pillars: (i) \emph{goal-scoped scientific decision governance} for \textbf{goal-oriented} research, with review gates and shared review surfaces; (ii) \emph{translate-then-reason} for \textbf{multimodal} input, routing scientific objects through domain translators before the agent reasons; (iii) \emph{evidence governance} for \textbf{auditable} traceability, linking claims to provenance chains and audit findings; (iv) \emph{collaborative team science} for \textbf{collaborative} research, enabling multi-role decision governance, with shared team workspaces planned for future releases; and (v) \emph{real-world application scenarios} for \textbf{practical} impact, demonstrated through eight end-to-end user cases, with flagship demonstrations including multi-day agentic research sprints for gene discovery, AI-guided de novo protein design, molecular optimization, and genome-to-BGC discovery. The system combines a thin interaction layer, contextual research capability patterns, an Agent Runtime and Workflow Engine, an Evidence-DAG audit sidecar and a Scientific Model Router. SciForge currently runs as a desktop application, with mobile supervision support; future releases will deepen team collaboration. The system is open-source and available at https://github.com/AGI4Sci/SciForge
