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

arXiv: https://arxiv.org/abs/2602.23335 · HTML: https://mlsanity.com/paper/2602.23335/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 42 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 11 of 11)

- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [Language agents achieve superhuman synthesis of scientific knowledge](https://mlsanity.com/paper/2409.13740/) (2024)
- [Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations](https://mlsanity.com/paper/2503.04761/) (2025)
- [Understanding User Experience in Large Language Model Interactions](https://mlsanity.com/paper/2401.08329/) (2024)
- [Investigating Affective Use and Emotional Well-being on ChatGPT](https://mlsanity.com/paper/2504.03888/) (2025)
- [Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies](https://mlsanity.com/paper/2309.13063/) (2023)
- [Anthropic Economic Index report: Uneven geographic and enterprise AI adoption](https://mlsanity.com/paper/2511.15080/) (2025)
- [State of AI: An Empirical 100 Trillion Token Study with OpenRouter](https://mlsanity.com/paper/2601.10088/) (2026)
- [The Adoption and Usage of AI Agents: Early Evidence from Perplexity](https://mlsanity.com/paper/2512.07828/) (2025)
- [Using LLMs to Investigate Correlations of Conversational Follow-up Queries with User Satisfaction](https://mlsanity.com/paper/2407.13166/) (2024)
- [Trapped by Expectations: Functional Fixedness in LLM-Enabled Chat Search](https://mlsanity.com/paper/2504.02074/) (2025)

## Built on by (most cited first, 2 of 2)

- [DRACULA: Hunting for the Actions Users Want Deep Research Agents to Execute](https://mlsanity.com/paper/2604.23815/) (2026)
- [Ream: Unfolding Mutual Awareness in Human-Agent Workspaces](https://mlsanity.com/paper/2610.09497/) (2026)

## Abstract (arXiv)

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.