AquiLLM: An Architecture for Supporting Tacit Knowledge Capture in Research Groups
Jack Stark, Srinath Saikrishnan, Vikram Seenivasan, Bernie Boscoe, Andrew Lizarraga, Tuan Do
cs.AI
Submitted: 2026-08-09
Updated: 2026-08-11
Comments: Accepted for publication in the NGEN-AI 2026 proceedings
Code: https://github.com/AquiLLM/AquiLLM
License: http://creativecommons.org/licenses/by/4.0/
The gist: Recent advances in retrieval-augmented generation (RAG) and large language models (LLMs) enable researchers to integrate AI into scientific workflows.
Terminology
Abstract
Recent advances in retrieval-augmented generation (RAG) and large language models (LLMs) enable researchers to integrate AI into scientific workflows. However, using proprietary commercial AI systems raises concerns about transparency, reproducibility and privacy, which are essential for scientific practices. To this end, AquiLLM was developed as an open-source modular RAG-LLM framework using open-weight models, designed to support research groups in capturing tacit knowledge. In this work, we present a series of architectural improvements and feature enhancements to AquiLLM, including local embedding and reranking, multimodal capabilities, OpenAI-compatible inference interfaces, user interface improvements, semantic and episodic memory capabilities, and skills support. These enhancements were informed by discussions with domain experts, including astrophysicists and environmental researchers, and represent a step toward AI systems more closely aligned with scientific research practices.
Sources
- On the Opportunities and Risks of Foundation Models
- AquiLLM: a RAG Tool for Capturing Tacit Knowledge in Research Groups
- Retrieval-Augmented Generation for Large Language Models: A Survey
- Multi-Modal Masked Autoencoders for Learning Image-Spectrum Associations for Galaxy Evolution and Cosmology
- Better Prompt Compression Without Multi-Layer Perceptrons
- Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- Evaluating Very Long-Term Conversational Memory of LLM Agents
- The Evolution of Reranking Models in Information Retrieval: From Heuristic Methods to Large Language Models
- Robust Speech Recognition via Large-Scale Weak Supervision
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- Cognitive Architectures for Language Agents
- Large language models in materials science and the need for open-source approaches
- The Science of Evaluating Foundation Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection