打造可审计的科学发现智能工作台，整合论文、代码、数据等多元科研资产。
SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery
- 用模块化服务实现搜索、推理、写作等自动化，保留人机协作界面
- 支持多模态输入与可追溯的证据链管理，确保研究过程透明可查
- 适合需要长期追踪、多人协作的复杂科研项目，如蛋白设计与基因发现
科学研究日益涉及异构科研对象——论文、代码、数据集、模型输出、图表、手稿及团队决策等，但通用AI助手难以保持这些成果作为连贯、可审计的研究状态。我们提出SciForge，一个面向科学发现的多模态原生工作台，将图形界面留给人工判断，而搜索、解析、模型调度、流程执行、绘图、写作和演示生成则以模块化代理服务运行。系统围绕五大支柱构建：(i) 目标导向的科研决策治理，设有审查节点与共享评审界面；(ii) 先转换后推理机制，对多模态输入通过领域翻译器处理再进行智能推理；(iii) 证据治理，实现主张与溯源链、审计结果的绑定；(iv) 协作式团队科研，支持多角色决策治理，未来版本将提供共享团队空间；(v) 真实应用场景验证，涵盖八个端到端用户案例，包括多日代理式基因发现、AI驱动的从头蛋白设计、分子优化及基因组到生物合成基因簇（BGC）的发现。系统包含轻量交互层、上下文科研能力模式、代理运行时与工作流引擎、证据-有向无环图（Evidence-DAG）审计侧车以及科学模型路由器。当前为桌面应用，支持移动端监控，后续将增强团队协作功能。系统开源，地址见 https://github.com/AGI4Sci/SciForge。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。