🤖 AI Summary
This study addresses the fragmentation of scientific knowledge systems and challenges in cross-user collaboration by proposing a hierarchical knowledge state and service governance framework. Replacing flat knowledge graphs with a five-layer FREG model, the approach integrates a router-contract-workflow microkernel architecture with LLM agents to enable unified encapsulation, secure exchange, and auditable recombination of research knowledge. Experimental validation in antibody design review demonstrates that this framework significantly enhances knowledge ingestion efficiency, cross-member integration capabilities, and support for scientific writing. Consequently, this work establishes a novel structured governance paradigm for open science ecosystems, effectively mitigating systemic fragmentation while facilitating secure and traceable collaborative research processes across diverse user groups.
📝 Abstract
As large language model (LLM) agents are increasingly adopted in scientific research, external knowledge bases, knowledge graphs, and long-term memory have improved information retrieval and task continuity. However, most structured knowledge systems remain node-centric, representing files, concepts, results, and judgments as nodes and relations in a graph. While suitable for personal knowledge management, such structures often depend on individual organizational practices, limiting knowledge sharing, integration, and reorganization across users. This paper presents Valhalla, a layered knowledge-state and service-governance framework for long-term scientific knowledge work. Valhalla replaces flat graphs with layered encapsulation and stable semantic boundaries through a five-layer File-Resource-Entity-Relationship-Graph (FREG) model. File and Resource preserve source identity and provenance, Entity represents knowledge objects, Relationship captures semantic judgments, and Graph provides task-oriented knowledge views, enabling knowledge states from different researchers to be exchanged and reorganized under a unified structure. We further introduce a Router-Contract-Workflow service-governance architecture, inspired by the microkernel paradigm, to constrain how language models access, modify, and extend knowledge states while maintaining structural consistency and auditable operational boundaries. We implement a Valhalla prototype and validate knowledge ingestion, cross-member integration, and scientific writing support through an antibody-design review task comprising 26 paper resources, 80 knowledge entities, and 92 semantic relations. Rather than proposing a new knowledge-extraction algorithm, Valhalla offers a paradigm for organizing collaborative scientific knowledge, transforming individualized knowledge structures into transferable and reorganizable shared knowledge states.