AgentSociety 2: An Integrated Research Environment for Executable Social Science

• URL: http://arxiv.org/abs/2607.11895v2
• Date: Wed, 15 Jul 2026 01:46:04 GMT
• Title: AgentSociety 2: An Integrated Research Environment for Executable Social Science
• Abstract summary: 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.
• Score: 29.070232222256365
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: AI scientist systems are beginning to automate parts of scientific research, but social science poses a distinct challenge: its objects of inquiry are not merely datasets or laboratory protocols, but integrated social processes involving situated participants, interaction contexts, interventions, and outcomes. Yet a critical link is missing: existing systems either assist isolated research tasks or simulate agents as experimental subjects, leaving the research workflow and simulated society decoupled. Here we introduce AgentSociety 2, an Integrated Research Environment for executable social science. 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; and silicon participants that generate behavioral responses within configurable social environments. This dual-role design turns hypotheses into auditable agent behaviors, environment rules, interventions, and measurements, thereby supporting an end-to-end workflow. Across seven illustrative studies spanning micro-level social-science laboratory experiments, meso-level dynamics in social media, and macro-level urban scenarios, we demonstrate its capacity to support diverse disciplinary questions, reproduce major qualitative patterns from prior studies, identify informative deviations, and enable large-scale simulations through optimized agent-environment interactions. By preserving human researchers' high-level agency while delegating procedural orchestration to agentic systems, it provides a human-in-the-loop and controllable infrastructure for next-generation computational social science, with broader applications in scalable computational social experimentation and AI-enabled social governance platforms.

Related papers

• Benchmarking AI Agents for Addressing Scientific Challenges Across Scales [118.2204632627895]
  SciAgentArena is a systematic benchmark for evaluating AI agents in real-world scientific research scenarios.<n>It comprises approximately 200 tasks with stepwise verification and an interactive, agent-agnostic environment for assessing diverse AI agents.<n>We find that current agents can contribute effectively to well-specified data-analysis, particularly when the task structure and evaluation criteria are clear.
  arXiv  Detail & Related papers  (2026-06-10T22:55:30Z)
• A Survey on LLM-based Conversational User Simulation [135.70167715992912]
  Large language models (LLMs) have enabled high-fidelity generation of synthetic user conversation.<n>We introduce a novel taxonomy covering user granularity and simulation objectives.<n>We aim to keep the research community informed of the latest advancements in conversational user simulation.
  arXiv  Detail & Related papers  (2026-04-27T20:22:42Z)
• LLM Agents as Social Scientists: A Human-AI Collaborative Platform for Social Science Automation [45.60301203002442]
  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.
  arXiv  Detail & Related papers  (2026-04-02T01:18:56Z)
• 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)
• IndoorWorld: Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environment [24.052929297990953]
  We introduce IndoorWorld, a heterogeneous multi-agent environment that tightly integrates physical and social dynamics.<n>We demonstrate the potential with a series of experiments within an office setting to examine the impact of multi-agent collaboration, resource competition, and spatial layout on agent behavior.
  arXiv  Detail & Related papers  (2025-06-14T03:44:09Z)
• ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows [82.07367406991678]
  Large Language Models (LLMs) have extended their impact beyond Natural Language Processing.<n>Among these, computer-using agents are capable of interacting with operating systems as humans do.<n>We introduce ScienceBoard, which encompasses a realistic, multi-domain environment featuring dynamic and visually rich scientific software.
  arXiv  Detail & Related papers  (2025-05-26T12:27:27Z)
• 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)
• Simulating Public Administration Crisis: A Novel Generative Agent-Based Simulation System to Lower Technology Barriers in Social Science Research [0.0]
  This article proposes a social simulation paradigm based on the GPT-3.5 large language model. It involves constructing Generative Agents that emulate human cognition, memory, and decision-making frameworks. Agents exhibit personalized customization, and public events are seamlessly incorporated through natural language processing.
  arXiv  Detail & Related papers  (2023-11-12T20:48:01Z)
• SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents [107.4138224020773]
  We present SOTOPIA, an open-ended environment to simulate complex social interactions between artificial agents and humans. In our environment, agents role-play and interact under a wide variety of scenarios; they coordinate, collaborate, exchange, and compete with each other to achieve complex social goals. We find that GPT-4 achieves a significantly lower goal completion rate than humans and struggles to exhibit social commonsense reasoning and strategic communication skills.
  arXiv  Detail & Related papers  (2023-10-18T02:27:01Z)
• PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception [50.551003004553806]
  We create a dataset of physically-grounded abstract social events, PHASE, that resemble a wide range of real-life social interactions. Phase is validated with human experiments demonstrating that humans perceive rich interactions in the social events. As a baseline model, we introduce a Bayesian inverse planning approach, SIMPLE, which outperforms state-of-the-art feed-forward neural networks.
  arXiv  Detail & Related papers  (2021-03-02T18:44:57Z)

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.