Understanding Usage and Engagement in AI-Powered Scientific Research Tools: The Asta Interaction Dataset

TL;DR

This paper introduces the Asta Interaction Dataset, analyzing how researchers interact with AI-powered scientific tools, revealing evolving query behaviors and engagement patterns in real-world research workflows.

Contribution

It provides the first large-scale dataset and analysis of user interactions with AI research tools, including a new query intent taxonomy for future system design and evaluation.

Findings

Users submit longer, complex queries than traditional search.

Users treat AI outputs as persistent, revisitable artifacts.

Engagement deepens with experience, but keyword queries persist.

Abstract

AI-powered scientific research tools are rapidly being integrated into research workflows, yet the field lacks a clear lens into how researchers use these systems in real-world settings. We present and analyze the Asta Interaction Dataset, a large-scale resource comprising over 200,000 user queries and interaction logs from two deployed tools (a literature discovery interface and a scientific question-answering interface) within an LLM-powered retrieval-augmented generation platform. Using this dataset, we characterize query patterns, engagement behaviors, and how usage evolves with experience. We find that users submit longer and more complex queries than in traditional search, and treat the system as a collaborative research partner, delegating tasks such as drafting content and identifying research gaps. Users treat generated responses as persistent artifacts, revisiting and navigating among outputs and cited evidence in non-linear ways. With experience, users issue more targeted queries and engage more deeply with supporting citations, although keyword-style queries persist even among experienced users. We release the anonymized dataset and analysis with a new query intent taxonomy to inform future designs of real-world AI research assistants and to support realistic evaluation.