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

arXiv: https://arxiv.org/abs/2606.09198 · HTML: https://mlsanity.com/paper/2606.09198/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 44 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 13 of 13)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [Evaluating Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2310.19736/) (2023)
- [Deep Research: A Survey of Autonomous Research Agents](https://mlsanity.com/paper/2508.12752/) (2025)
- [AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents](https://mlsanity.com/paper/2502.05957/) (2025)
- [ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents](https://mlsanity.com/paper/2407.03884/) (2024)
- [MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework](https://mlsanity.com/paper/2504.21582/) (2025)
- [DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision](https://mlsanity.com/paper/2510.05691/) (2025)
- [RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context](https://mlsanity.com/paper/2511.18743/) (2025)
- [SALM: A Multi-Agent Framework for Language Model-Driven Social Network Simulation](https://mlsanity.com/paper/2505.09081/) (2025)
- [Auto-Parallelizing Large Models with Rhino: A Systematic Approach on Production AI Platform](https://mlsanity.com/paper/2302.08141/) (2023)
- [Autono: A ReAct-Based Highly Robust Autonomous Agent Framework](https://mlsanity.com/paper/2504.04650/) (2025)

## Abstract (arXiv)

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.