TIB AIssistant: a Platform for AI-Supported Research Across Research Life Cycles

2025-12-18

AI Summary

To address low research efficiency and poor reproducibility of scholarly outputs, this paper proposes an AI-augmented platform spanning the entire research lifecycle. The platform adopts a modular multi-agent architecture, integrating domain-specific assistants for literature review, experimental design, and scientific writing, and enables cross-stage task coordination via an academic API gateway, knowledge graph–based retrieval, and structured data storage. It introduces the first deep integration of the RO-Crate standard into AI-driven research workflows, supporting end-to-end data provenance tracking and one-click reproducible packaging. Empirical evaluation demonstrates end-to-end automation—from research topic identification to initial manuscript generation. This work establishes a systematic paradigm and technical foundation for building transparent, reproducible, and scalable AI-powered research infrastructure.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Intelligent Robots: Embodied AI

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The rapidly growing popularity of adopting Artificial Intelligence (AI), and specifically Large Language Models (LLMs), is having a widespread impact throughout society, including the academic domain. AI-supported research has the potential to support researchers with tasks across the entire research life cycle. In this work, we demonstrate the TIB AIssistant, an AI-supported research platform providing support throughout the research life cycle. The AIssistant consists of a collection of assistants, each responsible for a specific research task. In addition, tools are provided to give access to external scholarly services. Generated data is stored in the assets and can be exported as an RO-Crate bundle to provide transparency and enhance reproducibility of the research project. We demonstrate the AIssistant's main functionalities by means of a sequential walk-through of assistants, interacting with each other to generate sections for a draft research paper. In the end, with the AIssistant, we lay the foundation for a larger agenda of providing a community-maintained platform for AI-supported research.

Problem

• Develops an AI-supported platform for research life cycles
• Integrates specialized assistants for specific research tasks
• Enhances transparency and reproducibility through data export

Innovation

• AI platform supports entire research life cycle
• Modular assistants handle specific research tasks
• RO-Crate export ensures transparency and reproducibility