arXiv:2511.14043v1 Announce Type: cross 
Abstract: AI Scientific Assistant Core (AISAC) is an integrated multi-agent system developed 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 general-purpose scientific assistance, demonstrating its cross-domain applicability.

نواة المساعد العلمي بالذكاء الاصطناعي (AISAC) هي نظام متعدد الوكلاء تم تطويره في مختبر أرجون الوطني لتحسين سير العمل العلمي والهندسي. يستخدم تقنيات راسخة مثل LangGraph للتنسيق، وFAISS للبحث المتجه، وSQLite لاستمرارية البيانات. يركز AISAC على الشفافية، وتتبع المصدر، والقدرة على التكيف في العمليات العلمية. يتضمن النظام سير عمل موجه-مخطط-منسق وأدوار مقيم اختيارية، مستخدمًا وكلاء مصممين عبر التعليمات لضمان مخرجات منظمة.

El Núcleo de Asistencia Científica por IA (AISAC) es un sistema multiagente desarrollado en el Laboratorio Nacional Argonne para mejorar los flujos de trabajo científicos y de ingeniería. Utiliza tecnologías establecidas como LangGraph para la orquestación, FAISS para la búsqueda vectorial y SQLite para la persistencia de datos. AISAC se centra en la transparencia, el seguimiento de la procedencia y la adaptabilidad en los procesos científicos. El sistema implementa un flujo de trabajo Router-Planner-Coordinator y roles opcionales de Evaluador, utilizando agentes diseñados por prompts para gar…

Le noyau d'assistance scientifique par IA (AISAC) est un système multi-agents développé au laboratoire national d'Argonne pour améliorer les flux de travail scientifiques et d'ingénierie. Il utilise des technologies établies telles que LangGraph pour l'orchestration, FAISS pour la recherche vectorielle et SQLite pour la persistance des données. AISAC met l'accent sur la transparence, le suivi de la provenance et l'adaptabilité dans les processus scientifiques. Le système comprend un flux de travail Router-Planner-Coordinator et des rôles d'évaluateur optionnels, utilisant des agents conçus par…

The AI Scientific Assistant Core (AISAC) is a multi-agent system developed at Argonne National Laboratory aimed at enhancing scientific and engineering workflows. It utilizes established technologies such as LangGraph for orchestration, FAISS for vector search, and SQLite for data persistence. AISAC focuses on transparency, provenance tracking, and adaptability in scientific processes. The system features a Router-Planner-Coordinator workflow and optional Evaluator roles, employing prompt-engineered agents to ensure structured outputs. A hybrid memory approach facilitates semantic retrieval an…

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

arXiv:2505.07917v2 Announce Type: replace-cross 
Abstract: Biomedical question-answering (QA) systems require effective retrieval and generation components to ensure accuracy, efficiency, and scalability. This study systematically examines a Retrieval-Augmented Generation (RAG) system for biomedical QA, evaluating retrieval strategies and response time trade-offs. We first assess state-of-the-art retrieval methods, including BM25, BioBERT, MedCPT, and a hybrid approach, alongside common data stores such as Elasticsearch, MongoDB, and FAISS, on a ~10% subset of PubMed (2.4M documents) to measure indexing efficiency, retrieval latency, and retriever performance in the end-to-end RAG system. Based on these insights, we deploy the final RAG system on the full 24M PubMed corpus, comparing different retrievers' impact on overall performance. Evaluations of the retrieval depth show that retrieving 50 documents with BM25 before reranking with MedCPT optimally balances accuracy (0.90), recall (0.90), and response time (1.91s). BM25 retrieval time remains stable (82ms), while MedCPT incurs the main computational cost. These results highlight previously not well-known trade-offs in retrieval depth, efficiency, and scalability for biomedical QA. With open-source code, the system is fully reproducible and extensible.

قدمت دراسة نظامًا لتوليد الأسئلة البيولوجية المعززة بالاسترجاع (RAG) ، حيث تم تقييم استراتيجيات الاسترجاع المختلفة وكفاءتها على مجموعة فرعية من بيانات PubMed. تقيم الدراسة طرقًا متطورة مثل BM25 و BioBERT ، وتقيس كفاءة الفهرسة وأداء الاسترجاع قبل نشر النظام على مجموعة بيانات PubMed الكاملة.

Un estudio ha presentado un sistema de Generación Aumentada por Recuperación (RAG) para la respuesta a preguntas biomédicas, evaluando diversas estrategias de recuperación y su eficiencia en un subconjunto de datos de PubMed. La investigación evalúa métodos de vanguardia como BM25 y BioBERT, midiendo la eficiencia de indexación y el rendimiento de recuperación antes de implementar el sistema en el corpus completo de PubMed.

Une étude a introduit un système de génération augmentée par récupération (RAG) pour le questionnement biomédical, évaluant diverses stratégies de récupération et leur efficacité sur un sous-ensemble de données de PubMed. La recherche évalue des méthodes à la pointe comme BM25 et BioBERT, mesurant l'efficacité de l'indexation et la performance de récupération avant de déployer le système sur l'ensemble du corpus de PubMed.

A study has introduced a Retrieval-Augmented Generation (RAG) system for biomedical question answering, evaluating various retrieval strategies and their efficiency on a subset of PubMed data. The research assesses state-of-the-art methods like BM25 and BioBERT, measuring indexing efficiency and retrieval performance before deploying the system on the full PubMed corpus.

Efficient and Reproducible Biomedical Question Answering using Retrieval Augmented Generation

One More Thing in AI – Your Shortcut to AI Mastery

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

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

Magicley AI

Sourcely

AI2sql

SnapChip

Ready to build your own newsroom?