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 -- and uses scholar-skill, a 26-skill plugin for Claude Code covering the full research pipeline from idea to submission across 18 orchestrated phases with 53 quality gates, 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 tacit field knowledge. The paper concludes with an analysis of three implications for the profession -- augmentation with fragile conditions, stratification risk, and a pedagogical crisis -- and proposes five principles for responsible vibe researching.
Figures & tables
Wave
Period
What was automated
What remained human
1
1970s–1990s
Computation (SPSS, Stata)
Reasoning, interpretation
2
2000s
Data collection (web, APIs)
Design, interpretation
3
2010s
Text analysis (NLP, ML)
Theory, framing
4
2024+
Multi-step reasoning
Open question
Table 1: Four Waves of Research Automation in the Social Sciences
Table 2: Scholar-Skill: 26 Skills Organized by Research Stage
Figure 1: Four cognitive task types in the research pipeline, classified by automation potential and tacit knowledge requirement. Type C tasks (execution) are the most automatable. Type A tasks (formulation) are the least.
Task
Codifiable?
Tacit?
Delegate?
Literature synthesis
High
Low
Yes
Method selection & code
High
Medium
Yes, with oversight
Analysis execution
High
Low
Yes
Prose drafting
Medium
Medium
Partially
RQ formulation
Low
High
AI assists only
Theory generation
Low
Very high
No
Table 3: The Delegation Framework: What to Delegate, What to Protect
Department of Electronic Engineering, Tsinghua University · School of Environment, Tsinghua University · School of Public Policy and Management, Tsinghua University +2
National Applied Research Laboratories Science & Technology Policy Research and Information Center Contact Address: 1, 14-15F, No. 106, Heping E. Rd., Sec. 2, Taipei 10636, Taiwan (R.O.C.)