MASS: Deep Research for Social Sciences with Memory-Augmented Social Simulation

• URL: http://arxiv.org/abs/2606.09198v1
• Date: Mon, 08 Jun 2026 08:32:21 GMT
• Title: MASS: Deep Research for Social Sciences with Memory-Augmented Social Simulation
• Abstract summary: "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.
• Score: 52.11732144306638
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep Research agents powered by Large Language Models (LLMs) have exhibited extraordinary potential in automated paper writing tasks. However, existing systems rely heavily on literature retrieval and synthesis through internet and local knowledge bases, often resulting research in lacking insight and creativity in social science. To address this issue, we propose "Memory-Augmented Social Simulation (MASS)", an innovative paradigm that leverages highly realistic and research-oriented social simulations to enhance the creativity and empirical founding of LLMs-generated research. 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. Together, these ensure simulation authenticity and provide a robust empirical foundation for generating innovative scholarly papers. Experimental results demonstrate the effectiveness of our method, showing a 6.81\% improvement in generation overall quality over foundation LLMs and 17.19\% gain in Insight over strong baselines.

Related papers

• 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)
• 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)
• Dynamic Knowledge Exchange and Dual-diversity Review: Concisely Unleashing the Potential of a Multi-Agent Research Team [53.38438460574943]
  IDVSCI is a multi-agent framework built on large language models (LLMs)<n>It incorporates two key innovations: a Dynamic Knowledge Exchange mechanism and a Dual-Diversity Review paradigm.<n>Results show that IDVSCI consistently achieves the best performance across two datasets.
  arXiv  Detail & Related papers  (2025-06-23T07:12:08Z)
• Large Language Model Driven Agents for Simulating Echo Chamber Formation [5.6488384323017]
  The rise of echo chambers on social media platforms has heightened concerns about polarization and the reinforcement of existing beliefs.<n>Traditional approaches for simulating echo chamber formation have often relied on predefined rules and numerical simulations.<n>We present a novel framework that leverages large language models (LLMs) as generative agents to simulate echo chamber dynamics.
  arXiv  Detail & Related papers  (2025-02-25T12:05:11Z)
• From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents [47.935533238820334]
  Traditional sociological research often relies on human participation, which, though effective, is expensive, challenging to scale, and with ethical concerns.<n>Recent advancements in large language models (LLMs) highlight their potential to simulate human behavior, enabling the replication of individual responses and facilitating studies on many interdisciplinary studies.<n>We categorize the simulations into three types: (1) Individual Simulation, which mimics specific individuals or demographic groups; (2) Scenario Simulation, where multiple agents collaborate to achieve goals within specific contexts; and (3) Simulation Society, which models interactions within agent societies to reflect the complexity and variety of real-world dynamics.
  arXiv  Detail & Related papers  (2024-12-04T18:56:37Z)
• LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities [0.0]
  Integrating large language models with agent-based simulations offers a transformational potential for understanding complex social systems. We explore architectures and methods to systematically develop LLM-augmented social simulations. We conclude that integrating LLMs with agent-based simulations offers a powerful toolset for researchers and scientists.
  arXiv  Detail & Related papers  (2024-05-08T08:57:54Z)
• CERN for AI: A Theoretical Framework for Autonomous Simulation-Based Artificial Intelligence Testing and Alignment [1.7586848727052424]
  This study investigates an innovative simulation-based multi-agent system within a virtual reality framework that replicates the real-world environment.<n>The framework is populated by automated 'digital citizens,' simulating complex social structures and interactions to examine and optimize AI.
  arXiv  Detail & Related papers  (2023-12-14T23:48:51Z)

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.