Organized Group Behavior Simulation

Simulating Organized Group Behavior: New Framework, Benchmark, and Analysis

Xinkai Zou*, Yiming Huang*, Zhuohang Wu, Jian Sha, Nan Huang, Longfei Yun, Jingbo Shang, Letian Peng

[Paper] [Code] [Dataset]

Abstract

Simulating how organized groups (e.g., corporations) make decisions (e.g., responding to a competitor’s move) is essential for understanding real-world dynamics and could benefit relevant applications (e.g., market prediction). In this paper, we formalize this problem as a concrete research platform for group behavior understanding, providing: (1) a task definition with benchmark and evaluation criteria, (2) a structured analytical framework with a corresponding algorithm, and (3) detailed temporal and cross-group analysis.

We introduce Organized Group Behavior Simulation, which models organized groups as collective entities. Given a group facing a particular situation, the task predicts the decision it would make. We present GROVE, a benchmark containing 44 entities with 8,052 real-world context-decision pairs from Wikipedia and TechCrunch across 9 domains, including evaluation protocols assessing consistency, initiative, scope, magnitude, and horizon.

Beyond basic prompting approaches, we propose a framework converting collective decision-making events into interpretable, adaptive, and traceable behavioral models, outperforming summarization and retrieval-based baselines. The approach includes an adapter mechanism for time-aware evolution and group-aware transfer, plus traceable evidence nodes grounding each decision rule in originating historical events. Analysis reveals temporal behavioral drift within individual groups, which the time-aware adapter effectively captures, and structured cross-group similarity enabling knowledge transfer for data-scarce organizations.

Links