LLM Agents as Social Scientists: A Human-AI Collaborative Platform for Social Science Automation

• URL: http://arxiv.org/abs/2604.01520v1
• Date: Thu, 02 Apr 2026 01:18:56 GMT
• Title: LLM Agents as Social Scientists: A Human-AI Collaborative Platform for Social Science Automation
• Abstract summary: S-Researcher is a large-scale social simulation system designed around three core requirements.<n>It supports researchers in designing social experiments, human behavior with LLM agents, analyzing results, and generating reports.<n>S-Researcher establishes a new human--AI collaborative paradigm for social science.
• Score: 45.60301203002442
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditional social science research often requires designing complex experiments across vast methodological spaces and depends on real human participants, making it labor-intensive, costly, and difficult to scale. Here we present S-Researcher, an LLM-agent-based platform that assists researchers in conducting social science research more efficiently and at greater scale by "siliconizing" both the research process and the participant pool. To build S-Researcher, we first develop YuLan-OneSim, a large-scale social simulation system designed around three core requirements: generality via auto-programming from natural language to executable scenarios, scalability via a distributed architecture supporting up to 100,000 concurrent agents, and reliability via feedback-driven LLM fine-tuning. Leveraging this system, S-Researcher supports researchers in designing social experiments, simulating human behavior with LLM agents, analyzing results, and generating reports, forming a complete human-AI collaborative research loop in which researchers retain oversight and intervention at every stage. We operationalize LLM simulation research paradigms into three canonical reasoning modes (induction, deduction, and abduction) and validate S-Researcher through systematic case studies: inductive reproduction of cultural dynamics consistent with Axelrod's theory, deductive testing of competing hypotheses on teacher attention validated against survey data, and abductive identification of a cooperation mechanism in public goods games confirmed by human experiments. S-Researcher establishes a new human--AI collaborative paradigm for social science, in which computational simulation augments human researchers to accelerate discovery across the full spectrum of social inquiry.

Related papers

• AgentSociety 2: An Integrated Research Environment for Executable Social Science [29.070232222256365]
  We introduce AgentSociety 2, an Integrated Research Environment for executable social science.<n>It couples two roles of LLM agents in the same runtime: AI social scientists that coordinate literature grounding, hypothesis generation, experiment design, simulation execution, result interpretation, and manuscript drafting.<n>This dual-role design turns hypotheses into auditable agent behaviors, environment rules, interventions, and measurements, thereby supporting an end-to-end workflow.
  arXiv  Detail & Related papers  (2026-06-11T10:41:23Z)
• MASS: Deep Research for Social Sciences with Memory-Augmented Social Simulation [52.11732144306638]
  "Memory-Augmented Social Simulation" (MASS) is an innovative paradigm that leverages highly realistic and research-oriented social simulations.<n>Specifically, MASS integrates three core components: dynamic goal-path planning with multi-level social norm restraint to guide the simulation, a multi-disciplinary behavior dataset for agent memory cold-start, and a structured forgetting mechanism inspired by the Ebbinghaus curve.
  arXiv  Detail & Related papers  (2026-06-08T08:32:21Z)
• Leveraging LLM-based agents for social science research: insights from citation network simulations [132.4334196445918]
  We introduce the CiteAgent framework, designed to generate citation networks based on human-behavior simulation.<n>CiteAgent captures predominant phenomena in real-world citation networks, including power-law distribution, citational distortion, and shrinking diameter.<n>We establish two LLM-based research paradigms in social science, allowing us to validate and challenge existing theories.
  arXiv  Detail & Related papers  (2025-11-05T08:47:04Z)
• Population-Aligned Persona Generation for LLM-based Social Simulation [58.84363795421489]
  We propose a systematic framework for synthesizing high-quality, population-aligned persona sets for social simulation.<n>Our approach begins by leveraging large language models to generate narrative personas from long-term social media data.<n>To address the needs of specific simulation contexts, we introduce a task-specific module that adapts the globally aligned persona set to targeted subpopulations.
  arXiv  Detail & Related papers  (2025-09-12T10:43:47Z)
• Epitome: Pioneering an Experimental Platform for AI-Social Science Integration [29.742040167436638]
  We introduce Epitome, the world's first open experimental platform dedicated to the deep integration of artificial intelligence and social science.<n>Epitome focuses on the interactive impacts of AI on individuals, organizations, and society during its real-world deployment.<n>With its canvas-style, user-friendly interface, Epitome enables researchers to easily design and run complex experimental scenarios.
  arXiv  Detail & Related papers  (2025-06-30T09:06:16Z)
• LLM Social Simulations Are a Promising Research Method [4.6456873975541635]
  We argue that the promise of LLM social simulations can be achieved by addressing five tractable challenges.<n>We believe that LLM social simulations can already be used for pilot and exploratory studies.<n>Researchers should prioritize developing conceptual models and iterative evaluations to make the best use of new AI systems.
  arXiv  Detail & Related papers  (2025-04-03T03:01:26Z)
• AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society [32.849311155921264]
  We propose AgentSociety, a large-scale social simulator that integrates a realistic societal environment.<n>Based on the proposed simulator, we generate social lives for over 10k agents, simulating their 5 million interactions.<n>We focus on four key social issues: polarization, the spread of inflammatory messages, the effects of universal basic income policies, and the impact of external shocks such as hurricanes.
  arXiv  Detail & Related papers  (2025-02-12T15:27:07Z)
• ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models [56.08917291606421]
  ResearchAgent is an AI-based system for ideation and operationalization of novel work.<n>ResearchAgent automatically defines novel problems, proposes methods and designs experiments, while iteratively refining them.<n>We experimentally validate our ResearchAgent on scientific publications across multiple disciplines.
  arXiv  Detail & Related papers  (2024-04-11T13:36:29Z)
• Large Language Model-based Human-Agent Collaboration for Complex Task Solving [94.3914058341565]
  We introduce the problem of Large Language Models (LLMs)-based human-agent collaboration for complex task-solving. We propose a Reinforcement Learning-based Human-Agent Collaboration method, ReHAC. This approach includes a policy model designed to determine the most opportune stages for human intervention within the task-solving process.
  arXiv  Detail & Related papers  (2024-02-20T11:03:36Z)
• Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspective [16.08517740276261]
  Computational experiments have emerged as a valuable method for studying complex systems. accurately representing real social systems in Agent-based Modeling (ABM) is challenging due to the diverse and intricate characteristics of humans. The integration of Large Language Models (LLMs) has been proposed, enabling agents to possess anthropomorphic abilities.
  arXiv  Detail & Related papers  (2024-02-01T01:17:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.