Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulations
This addresses the problem of unreliable agent behaviors in high-stakes social simulations for applications like training and policy-making, representing a novel method for a known bottleneck.
The paper tackled the Behavior-Realism Gap in language-driven generative agents by introducing the Persona-Environment Behavioral Alignment (PEBA) framework and PersonaEvolve (PEvo) algorithm, achieving an 84% reduction in distributional divergence and 34% improvement over baselines in an active shooter simulation.
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.