# Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulations

arXiv: https://arxiv.org/abs/2509.16457 · HTML: https://mlsanity.com/paper/2509.16457/

## Key facts

- Cited by 4 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 13 of its 26 references that are in the map.
- First posted on arXiv 19 Sep 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, 13 of 13)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals](https://mlsanity.com/paper/2411.10109/) (2024)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [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)
- [Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs](https://mlsanity.com/paper/2403.05020/) (2024)
- [Project Sid: Many-agent simulations toward AI civilization](https://mlsanity.com/paper/2411.00114/) (2024)
- [Simulating Public Administration Crisis: A Novel Generative Agent-Based Simulation System to Lower Technology Barriers in Social Science Research](https://mlsanity.com/paper/2311.06957/) (2023)
- [Sense and Sensitivity: Evaluating the simulation of social dynamics via Large Language Models](https://mlsanity.com/paper/2412.05093/) (2024)
- [Static network structure cannot stabilize cooperation among Large Language Model agents](https://mlsanity.com/paper/2411.10294/) (2024)
- [Enhancing Building Safety Design for Active Shooter Incidents: Exploration of Building Exit Parameters using Reinforcement Learning-Based Simulations](https://mlsanity.com/paper/2407.10441/) (2024)

## Built on by (most cited first, 4 of 4)

- [RealUserSim: Bridging the Reality Gap in Agent Benchmarking via Grounded User Simulation](https://mlsanity.com/paper/2605.20204/) (2026)
- [The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment](https://mlsanity.com/paper/2605.07462/) (2026)
- [PERCEIVE: A Benchmark for Personalized Emotion and Communication Behavior Understanding on Social Media](https://mlsanity.com/paper/2605.12525/) (2026)
- [PsyBer-Agent: A Psychology-Driven User Agent for Recommender Systems](https://mlsanity.com/paper/2610.13989/) (2026)

## Abstract (arXiv)

Language-driven generative agents have enabled large-scale social simulations with transformative uses, from interpersonal training to aiding global policy-making. However, recent studies indicate that generative agent behaviors often deviate from expert expectations and real-world data--a phenomenon we term the Behavior-Realism Gap. To address this, we introduce a theoretical framework called Persona-Environment Behavioral Alignment (PEBA), formulated as a distribution matching problem grounded in Lewin's behavior equation stating that behavior is a function of the person and their environment. Leveraging PEBA, we propose PersonaEvolve (PEvo), an LLM-based optimization algorithm that iteratively refines agent personas, implicitly aligning their collective behaviors with realistic expert benchmarks within a specified environmental context. We validate PEvo in an active shooter incident simulation we developed, achieving an 84% average reduction in distributional divergence compared to no steering and a 34% improvement over explicit instruction baselines. Results also show PEvo-refined personas generalize to novel, related simulation scenarios. Our method greatly enhances behavioral realism and reliability in high-stakes social simulations. More broadly, the PEBA-PEvo framework provides a principled approach to developing trustworthy LLM-driven social simulations.