AgenticScholar: Agentic Data Management with Pipeline Orchestration for Scholarly Corpora
This addresses the problem of scalable and unified data management for researchers and scholars, though it appears incremental as it builds on existing agentic and RAG concepts.
The paper tackles the challenge of managing and querying large scholarly corpora by proposing AgenticScholar, a system that integrates knowledge representation, query planning, and execution to handle diverse query types, and it demonstrates significant improvements in effectiveness, efficiency, and interpretability over existing systems.
Managing the rapidly growing scholarly corpus poses significant challenges in representation, reasoning, and efficient analysis. An ideal system should unify structured knowledge management, agentic planning, and interpretable execution to support diverse scholarly queries - from retrieval to knowledge discovery and generation - at scale. Unfortunately, existing RAG and document analytics systems fail to achieve all query types simultaneously. To this end, we propose AgenticScholar, an agentic scholarly data management system that integrates a structure-aware knowledge representation layer, an LLM-centric hybrid query planning layer, and a unified execution layer with composable operators. AgenticScholar autonomously translates natural language queries into executable DAG plans, enabling end-to-end reasoning over multi-modal scholarly data. Extensive experiments demonstrate that AgenticScholar significantly outperforms existing systems in effectiveness, efficiency, and interpretability, offering a practical foundation for future research on agentic scholarly data management.