Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

APS: Bias-Controlled Adaptive Prototype Simulation for Population-Scale LLM Agents

About

LLM-agent simulation offers a flexible computational tool for studying population response trajectories that depend on scenario events, memory, demographics, and evolving social context. However, full multi-round simulation scales linearly with both population size and horizon, requiring every agent to query the LLM at every round. We propose Adaptive Prototype Simulation (APS), a framework that reframes scalable LLM-based simulation as a recurrent oracle-allocation problem. APS retains the designated LLM as the online transition oracle while querying adaptive core prototypes, selected singleton-tail agents, and shadow-audit agents. Prototype responses induce local response surfaces for nearby agents, reducing online LLM calls without replacing the underlying transition model. To control approximation bias, shadow-audit residual correction estimates propagation residuals for aggregate correction and future budget allocation, while tail-protected singleton routing directly queries selected isolated, heterogeneous, or high-curvature regions that are vulnerable to smoothing. Theoretically, we treat APS as an estimator for full-scale high-precision individual social simulation and decompose its errors into prototype-coverage error, shadow-audit residual-correction error, local-propagation bias, and temporal context mismatch. Under the reported protocols, APS gives lower reference-aligned distributional discrepancy than scale-oriented and same-budget baselines while reducing online LLM calls, with ablations and compact robustness checks diagnosing the main bias-control mechanisms. In a 10M-agent, multi-round public-opinion simulation, APS achieves a 381.1-fold reduction over full simulation, with reference-aligned final-round JSD of 0.094 against the corresponding full-LLM reference.

Quan Zheng, Yan Gao, Shaobin He, Haoxiang Guan, Yuanhe Tian, Jie Feng, Ming Wang, Shuxin Zheng, Zhen Liu• 2026

Related benchmarks

TaskDatasetResultRank
Social SimulationWVS-derived population 1M scale
LLM Calls83.4
3
Social SimulationWVS-derived population 10M agents
LLM Calls209.9
3
Social SimulationWVS-derived population 10K agents
LLM Calls20.8
3
Social SimulationWVS-derived population (100K agents)
LLM Calls172
3
Social SimulationWVS-derived population 3K agents
LLM Calls8.9
1
Showing 5 of 5 rows

Other info

Follow for update