# HAG: Hierarchical Demographic Tree-based Agent Generation for Topic-Adaptive Simulation

arXiv: https://arxiv.org/abs/2601.05656 · HTML: https://mlsanity.com/paper/2601.05656/

## 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 19 of its 38 references that are in the map.
- First posted on arXiv 9 Jan 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, 19 of 19)

- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives](https://mlsanity.com/paper/2312.11970/) (2023)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities](https://mlsanity.com/paper/2310.10436/) (2023)
- [OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://mlsanity.com/paper/2411.11581/) (2024)
- [LLM Generated Persona is a Promise with a Catch](https://mlsanity.com/paper/2503.16527/) (2025)
- [WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Models](https://mlsanity.com/paper/2404.16308/) (2024)
- [SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users](https://mlsanity.com/paper/2504.10157/) (2025)
- [A Survey on LLM-powered Agents for Recommender Systems](https://mlsanity.com/paper/2502.10050/) (2025)
- [Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles](https://mlsanity.com/paper/2502.18968/) (2025)
- [LLMs generate structurally realistic social networks but overestimate political homophily](https://mlsanity.com/paper/2408.16629/) (2024)
- [LLM-based Human Simulations Have Not Yet Been Reliable](https://mlsanity.com/paper/2501.08579/) (2025)
- [Population-Aligned Persona Generation for LLM-based Social Simulation](https://mlsanity.com/paper/2509.10127/) (2025)
- [Mixture-of-Personas Language Models for Population Simulation](https://mlsanity.com/paper/2504.05019/) (2025)
- [Agentic Feedback Loop Modeling Improves Recommendation and User Simulation](https://mlsanity.com/paper/2410.20027/) (2024)
- [Noise, Adaptation, and Strategy: Assessing LLM Fidelity in Decision-Making](https://mlsanity.com/paper/2508.15926/) (2025)
- [Multi-Personality Generation of LLMs at Decoding-time](https://mlsanity.com/paper/2511.01891/) (2025)

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

- [Parametric Social Identity Injection and Diversification in Public Opinion Simulation](https://mlsanity.com/paper/2603.16142/) (2026)

## Abstract (arXiv)

High-fidelity agent initialization is crucial for credible Agent-Based Modeling across diverse domains. A robust framework should be Topic-Adaptive, capturing macro-level joint distributions while ensuring micro-level individual rationality. Existing approaches fall into two categories: static data-based retrieval methods that fail to adapt to unseen topics absent from the data, and LLM-based generation methods that lack macro-level distribution awareness, resulting in inconsistencies between micro-level persona attributes and reality. To address these problems, we propose HAG, a Hierarchical Agent Generation framework that formalizes population generation as a two-stage decision process. Firstly, utilizing a World Knowledge Model to infer hierarchical conditional probabilities to construct the Topic-Adaptive Tree, achieving macro-level distribution alignment. Then, grounded real-world data, instantiation and agentic augmentation are carried out to ensure micro-level consistency. Given the lack of specialized evaluation, we establish a multi-domain benchmark and a comprehensive PACE evaluation framework. Extensive experiments show that HAG significantly outperforms representative baselines, reducing population alignment errors by an average of 37.7% and enhancing sociological consistency by 18.8%.