构建可自演化科学助手，突破现有AI科研工具的稳定性与交互瓶颈
BloClaw: An Omniscient, Multi-Modal Agentic Workspace for Next-Generation Scientific Discovery
- 用双轨路由协议替代脆弱JSON，错误率从17.6%降至0.2%
- 通过动态补丁捕获绘图结果，绕过浏览器跨域限制
- 界面可智能切换命令行与3D可视化，适合复杂科研数据处理
将大语言模型引入生命科学催生了“AI科学家”，但现有框架在部署中暴露出严重基础设施缺陷：依赖易出错的JSON工具调用、执行沙箱无法保留图形输出、对话界面难以处理高维科学数据。我们提出BloClaw——一个面向人工智能科学（AI4S）的统一多模态操作系统。通过三项创新重构人机交互范式：(1) 双轨路由协议（XML-Regex），将序列化错误率从17.6%降至0.2%；(2) 运行时状态拦截沙箱，利用Python猴子补丁自动捕获并编译动态可视化（Plotly/Matplotlib），规避浏览器CORS策略；(3) 状态驱动的动态视口界面，可在极简命令面板与交互式空间渲染引擎间无缝切换。我们在化学信息学（RDKit）、ESMFold从头设计三维蛋白折叠、分子对接及自主检索增强生成（RAG）任务上全面评估，验证其高度鲁棒且自演化的计算研究助理能力。开源代码已发布于https://github.com/qinheming/BloClaw。
原文摘要 · Abstract (English)
The integration of Large Language Models (LLMs) into life sciences has catalyzed the development of "AI Scientists." However, translating these theoretical capabilities into deployment-ready research environments exposes profound infrastructural vulnerabilities. Current frameworks are bottlenecked by fragile JSON-based tool-calling protocols, easily disrupted execution sandboxes that lose graphical outputs, and rigid conversational interfaces inherently ill-suited for high-dimensional scientific data.We introduce BloClaw, a unified, multi-modal operating system designed for Artificial Intelligence for Science (AI4S). BloClaw reconstructs the Agent-Computer Interaction (ACI) paradigm through three architectural innovations: (1) An XML-Regex Dual-Track Routing Protocol that statistically eliminates serialization failures (0.2% error rate vs. 17.6% in JSON); (2) A Runtime State Interception Sandbox that utilizes Python monkey-patching to autonomously capture and compile dynamic data visualizations (Plotly/Matplotlib), circumventing browser CORS policies; and (3) A State-Driven Dynamic Viewport UI that morphs seamlessly between a minimalist command deck and an interactive spatial rendering engine. We comprehensively benchmark BloClaw across cheminformatics (RDKit), de novo 3D protein folding via ESMFold, molecular docking, and autonomous Retrieval-Augmented Generation (RAG), establishing a highly robust, self-evolving paradigm for computational research assistants. The open-source repository is available at https://github.com/qinheming/BloClaw.
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。