Tag
The paper proposes MAGG, a multi-agent framework for constructing governed knowledge graphs with domain-expert review, improving knowledge extraction and question-answering performance over methods like Microsoft GraphRAG.
This paper introduces a production enterprise analytics system that inverts the interaction model from question-first to analyst-first through domain-expert skills and knowledge compilation, enabling proactive analytics with verified metrics and suggested questions.
Presents FOCUS, a fine-tuning method that decouples expert personas in LLMs via orthogonal decomposition and an expert gating module, improving domain-specific task accuracy across financial, legal, and medical benchmarks.