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

TL;DR

AISAC is a modular, transparent multi-agent system designed to support evidence-grounded scientific reasoning with guarantees for transparency, reproducibility, and role-based memory management.

Contribution

It provides a governed execution framework with explicit role semantics, budgeted context, traceability, and extensibility for deploying AI in scientific research.

Findings

Deployed in combustion science, materials research, and energy safety workflows.

Enforces structural guarantees like role semantics, budget limits, and traceability.

Supports reproducible, transparent scientific reasoning with hybrid memory and retrieval.

Abstract

AI Scientific Assistant Core (AISAC) is a transparent, modular multi-agent runtime developed at Argonne National Laboratory to support long-horizon, evidence-grounded scientific reasoning. Rather than proposing new agent algorithms or claiming autonomous scientific discovery, AISAC contributes a governed execution substrate that operationalizes key requirements for deploying agentic AI in scientific practice, including explicit role semantics, budgeted context management, traceable execution, and reproducible interaction with tools and knowledge. AISAC enforces four structural guarantees for scientific reasoning: (1) declarative agent registration with runtime-enforced role semantics and automatic system prompt generation; (2) budgeted orchestration via explicit per-turn context and delegation depth limits; (3) role-aligned memory access across episodic, dialogue, and evidence layers; and (4) trace-driven transparency through persistent execution records and a live event-stream interface. These guarantees are implemented through hybrid persistent memory (SQLite and dual FAISS indices), governed retrieval with agent-scoped RAG, structured tool execution with schema validation, and a configuration-driven bootstrap mechanism that enables project specific extension without modifying the shared core. AISAC is currently deployed across multiple scientific workflows at Argonne, including combustion science, materials research, and energy process safety, demonstrating its use as a reusable substrate for domain-specialized AI scientific assistants.