←Back to feed
🧠 AI🟢 BullishImportance 6/10
Understanding Usage and Engagement in AI-Powered Scientific Research Tools: The Asta Interaction Dataset
arXiv – CS AI|Dany Haddad, Dan Bareket, Joseph Chee Chang, Jay DeYoung, Jena D. Hwang, Uri Katz, Mark Polak, Sangho Suh, Harshit Surana, Aryeh Tiktinsky, Shriya Atmakuri, Jonathan Bragg, Mike D'Arcy, Sergey Feldman, Amal Hassan-Ali, Rub\'en Lozano, Bodhisattwa Prasad Majumder, Charles McGrady, Amanpreet Singh, Brooke Vlahos, Yoav Goldberg, Doug Downey||7 views
🤖AI Summary
Researchers released the Asta Interaction Dataset containing over 200,000 user queries from AI-powered scientific research tools, revealing how scientists interact with LLM-based research assistants. The study shows users treat these systems as collaborative research partners, submitting longer queries and using outputs as persistent artifacts for non-linear exploration.
Key Takeaways
- →The dataset includes 200,000+ user queries from deployed AI scientific research tools within an LLM-powered platform.
- →Users submit longer and more complex queries compared to traditional search engines when using AI research tools.
- →Researchers treat AI systems as collaborative partners, delegating tasks like content drafting and identifying research gaps.
- →Users engage with AI-generated responses as persistent artifacts, revisiting outputs and citations in non-linear patterns.
- →Experienced users develop more targeted querying behavior and engage more deeply with supporting citations over time.
#ai-research#llm#scientific-tools#dataset#user-behavior#research-workflows#retrieval-augmented-generation#academic-research
Read Original →via arXiv – CS AI
Act on this with AI
Stay ahead of the market.
Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.
Related Articles