![[2602.22401] Vibe Researching as Wolf Coming: Can AI Agents with Skills Replace or Augment Social Scientists?](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.22401] Vibe Researching as Wolf Coming: Can AI Agents with Skills Replace or Augment Social Scientists?
Summary
This paper explores the potential of AI agents to replace or augment social scientists by introducing the concept of 'vibe researching,' which leverages AI's capabilities in executing research workflows autonomously.
Why It Matters
As AI technology evolves, understanding its implications for social science is crucial. This research highlights how AI can enhance research efficiency while also raising concerns about the potential loss of theoretical originality and the need for responsible integration of AI in academic practices.
Key Takeaways
- AI agents can autonomously execute entire research pipelines, enhancing efficiency.
- The concept of 'vibe researching' parallels 'vibe coding' and emphasizes AI's role in social science.
- AI excels in speed and methodological support but lacks in theoretical originality.
- The integration of AI in research raises concerns about stratification and pedagogical challenges.
- Five principles for responsible vibe researching are proposed to guide AI's use in academia.
Computer Science > Artificial Intelligence arXiv:2602.22401 (cs) [Submitted on 25 Feb 2026] Title:Vibe Researching as Wolf Coming: Can AI Agents with Skills Replace or Augment Social Scientists? Authors:Yongjun Zhang View a PDF of the paper titled Vibe Researching as Wolf Coming: Can AI Agents with Skills Replace or Augment Social Scientists?, by Yongjun Zhang View PDF HTML (experimental) Abstract:AI agents -- systems that execute multi-step reasoning workflows with persistent state, tool access, and specialist skills -- represent a qualitative shift from prior automation technologies in social science. Unlike chatbots that respond to isolated queries, AI agents can now read files, run code, query databases, search the web, and invoke domain-specific skills to execute entire research pipelines autonomously. This paper introduces the concept of vibe researching -- the AI-era parallel to ``vibe coding'' (Karpathy, 2025) -- and uses scholar-skill, a 21-skill plugin for Claude Code covering the full research pipeline from idea to submission, as an illustrative case. I develop a cognitive task framework that classifies research activities along two dimensions -- codifiability and tacit knowledge requirement -- to identify a delegation boundary that is cognitive, not sequential: it cuts through every stage of the research pipeline, not between stages. I argue that AI agents excel at speed, coverage, and methodological scaffolding but struggle with theoretical originality and tac...