Beyond static responses: multi-agent LLM systems as a new paradigm for social science research
За пределами статичных ответов: мультиагентные системы на основе больших языковых моделей как новая парадигма исследований в социальных науках
2026-09-02
SCID: 54.1/3fv3gp26
Discuss with AI
agentic LLM systemsemergent social dynamicsmulti-agent LLM systemssocial science researchstandardized evaluation metrics
Figures from the paper
Abstract (AI)
Abstract As large language models (LLMs) transition from static tools to fully agentic systems, their potential for transforming social science research is well recognized. This paper introduces a structured framework for understanding the diverse applications of agentic LLM systems, ranging from simple data processors to complex, multi-agent systems capable of simulating emergent social dynamics. By mapping this developmental continuum across six levels, the paper clarifies the technical and methodological boundaries between different agentic architectures, surveying current capabilities and future potential. It highlights how lower-tier systems streamline conventional tasks like text classification and data annotation, while higher-tier systems enable new forms of inquiry, including the study of group dynamics, norm formation, and large-scale social processes. However, these advancements also raise challenges around reproducibility, ethical oversight, and emergent biases. The paper critically examines these concerns, arguing for sound validation methods, interdisciplinary collaboration, and standardized evaluation metrics. It argues that while agentic LLM systems offer considerable potential for the social sciences, using them responsibly will require careful, context-sensitive deployment and ongoing methodological refinement. The paper concludes with a call for future research that balances technical innovation with ethical responsibility, working toward agentic systems that not only replicate but also extend social science methodology.
Key Findings
1
Agentic LLM adoption raises challenges involving reproducibility, ethical oversight, and emergent biases, requiring robust validation and standardized evaluation metrics.
2
Lower-level agentic systems support conventional tasks such as text classification and data annotation, while higher-level systems simulate group dynamics, norm formation, and large-scale social processes.
3
Multi-agent LLM systems may enable new forms of social-science inquiry by modeling emergent social dynamics beyond static-response approaches.
4
Responsible deployment requires context-sensitive use, interdisciplinary collaboration, and continued methodological refinement to balance innovation with ethical responsibility.
5
The paper presents a six-level framework organizing agentic LLM applications in social science, from basic data processing to complex multi-agent systems.
Research Object
agentic large language model (LLM) systems used in social science research
Research Subject
their application capabilities, developmental architectures, methodological boundaries, and implications for studying social dynamics and conducting social science research
Publication Details
Publication Date
2026-09-02
Journal
Publisher
ISSN
Cited by
25
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai8
A survey on large language model based autonomous agents2024
Generative Agents: Interactive Simulacra of Human Behavior2023
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery2024
Autonomous chemical research with large language models2023
Can Large Language Models Transform Computational Social Science?2023
AI and the transformation of social science research2023
Can Generative AI improve social science?2024
Accelerating scientific discovery with Co-Scientist2026