AISAC: An Integrated multi-agent System for Transparent, Retrieval-Grounded Scientific Assistance

AI Scientific Assistant Core (AISAC) is an integrated multi-agent system deployed at Argonne National Laboratory for scientific and engineering workflows. AISAC builds on established technologies-LangGraph for orchestration, FAISS for vector search, and SQLite for persistence-and integrates them into a unified system prototype focused on transparency, provenance tracking, and scientific adaptability. The system implements a Router-Planner-Coordinator workflow and an optional Evaluator role, using prompt-engineered agents coordinated via LangGraph’s StateGraph and supported by helper agents such as a Researcher. Each role is defined through custom system prompts that enforce structured JSON outputs. A hybrid memory approach (FAISS + SQLite) enables both semantic retrieval and structured conversation history. An incremental indexing strategy based on file hashing minimizes redundant re-embedding when scientific corpora evolve. A configuration-driven project bootstrap layer allows research teams to customize tools, prompts, and data sources without modifying core code. All agent decisions, tool invocations, and retrievals are logged and visualized through a custom Gradio interface, providing step-by-step transparency for each reasoning episode. The authors have applied AISAC to multiple research areas at Argonne, including specialized deployments for waste-to-products research and energy process safety, as well as generalpurpose scientific assistance, demonstrating its cross-domain applicability. AISAC is not a new model architecture. Its contribution is a system-engineering blueprint for AI scientific assistance, consisting of: (1) a practical integration blueprint for transparent, retrieval-grounded multi-agent scientific assistance; and (2) a reusable, configuration-driven core that supports project-level specialization, provenance tracking, and persistent memory.