# Integrating LLM and Diffusion-Based Agents for Social Simulation

arXiv: https://arxiv.org/abs/2510.16366 · HTML: https://mlsanity.com/paper/2510.16366/

## Key facts

- Cited by 1 papers in the map (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 20 of its 60 references that are in the map.
- First posted on arXiv 18 Oct 2025.

## 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, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network](https://mlsanity.com/paper/1808.03314/) (2018)
- [User Behavior Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2306.02552/) (2023)
- [AgentScope: A Flexible yet Robust Multi-Agent Platform](https://mlsanity.com/paper/2402.14034/) (2024)
- [From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents](https://mlsanity.com/paper/2412.03563/) (2024)
- [KuaiRand: An Unbiased Sequential Recommendation Dataset with Randomly Exposed Videos](https://mlsanity.com/paper/2208.08696/) (2022)
- [Unveiling the Truth and Facilitating Change: Towards Agent-based Large-scale Social Movement Simulation](https://mlsanity.com/paper/2402.16333/) (2024)
- [DiffNet++: A Neural Influence and Interest Diffusion Network for Social Recommendation](https://mlsanity.com/paper/2002.00844/) (2020)
- [Y Social: an LLM-powered Social Media Digital Twin](https://mlsanity.com/paper/2408.00818/) (2024)
- [CitySim: Modeling Urban Behaviors and City Dynamics with Large-Scale LLM-Driven Agent Simulation](https://mlsanity.com/paper/2506.21805/) (2025)
- [Topological Recurrent Neural Network for Diffusion Prediction](https://mlsanity.com/paper/1711.10162/) (2017)
- [Creating a Large Language Model of a Philosopher](https://mlsanity.com/paper/2302.01339/) (2023)
- [Modeling echo chambers and polarization dynamics in social networks](https://mlsanity.com/paper/1906.12325/) (2019)
- [MINDECHO: Role-Playing Language Agents for Key Opinion Leaders](https://mlsanity.com/paper/2407.05305/) (2024)
- [A Large-Scale Rich Context Query and Recommendation Dataset in Online Knowledge-Sharing](https://mlsanity.com/paper/2106.06467/) (2021)
- [DyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users' Dynamic Preferences for Information Diffusion Prediction](https://mlsanity.com/paper/2006.05169/) (2020)
- [Neural Diffusion Model for Microscopic Cascade Prediction](https://mlsanity.com/paper/1812.08933/) (2018)
- [A Survey of Datasets for Information Diffusion Tasks](https://mlsanity.com/paper/2407.05161/) (2024)

## Built on by (most cited first, 1 of 1)

- [From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models](https://mlsanity.com/paper/2608.06020/) (2026)

## Abstract (arXiv)

Large language models (LLMs) offer strong semantic reasoning capabilities for user modeling, but applying LLM-based simulation to an entire social network is computationally expensive and often unreliable for users with sparse behavioral histories. Meanwhile, conventional information diffusion models efficiently exploit historical propagation patterns and social structures, but provide limited understanding of item content and user-item semantic compatibility. We propose HySID, a hybrid framework for individual-level information adoption prediction that combines semantic reasoning with structural diffusion. HySID first analyzes the historical user-relation graph to adaptively select a small set of structurally informative core users. It then applies LLM-based simulation to estimate the engagement of these users and converts the judgments into a diffusion-compatible seed. Finally, a plug-in diffusion backbone propagates this seed through historical interaction structures to rank potential adopters across the full user population. This design enables LLMs to focus on users for whom semantic reasoning is most informative while allowing neural diffusion models to generalize the evidence to users that are not explicitly simulated. Experiments on three real-world datasets from Weibo, Zhihu, and KuaiRand show that HySID consistently improves four diffusion backbones in Recall and NDCG, while outperforming full-population LLM simulation baselines. At the same time, selective simulation reduces LLM inference cost by approximately 83% to 99.9%, demonstrating that HySID provides an effective and computationally practical approach to scalable information adoption prediction.