Search papers, labs, and topics across Lattice.
BloClaw is introduced as a multi-modal operating system for AI4S, addressing infrastructural vulnerabilities in current LLM-based research environments. It employs an XML-Regex Dual-Track Routing Protocol to reduce serialization failures, a Runtime State Interception Sandbox for capturing dynamic visualizations, and a State-Driven Dynamic Viewport UI for flexible interaction. Benchmarking across cheminformatics, protein folding, molecular docking, and RAG demonstrates BloClaw's robustness as a self-evolving computational research assistant.
JSON tool-calling is so fragile it's practically unusable: BloClaw offers a 98.8% success rate with its novel XML-Regex Dual-Track Routing Protocol.
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.
