Search papers, labs, and topics across Lattice.
This study addresses the limitations of static-profile agents in large language models (LLMs) by introducing LifeMem, a longitudinal memory framework that enhances the integration of individual experiences. The authors demonstrate that traditional methods lead to identity essentialism, where demographic labels distort individual traits, resulting in less diversity in responses. By employing LifeMem, the researchers show significant improvements in aligning LLM outputs with human-like response distributions and within-group diversity, suggesting a more nuanced approach to social simulation in AI agents.
Static profiles lead to identity essentialism in LLMs, but a new longitudinal memory framework reveals a path to richer, more diverse social simulations.
Large language models (LLMs) offer a scalable approach to social simulation, but their credibility depends on how agents are constructed. Existing methods can partially reproduce population-level patterns, yet often fail to capture human-like diversity. Our analysis shows that static-profile agents exhibit stronger demographic separation and within-group compression than humans, a pattern consistent with identity essentialism: demographic labels can encourage models to treat group-average tendencies as individual traits, homogenizing responses within groups. We argue that this limitation arises from two related factors: sparse, static agent representations and the limited ability of prompt-only memory to persistently integrate experience. Inspired by complementary memory systems, we propose LifeMem, a longitudinal memory framework that combines structured life-event retrieval with agent-specific parametric memory for experience integration. Experiments on Add Health and Understanding Society with three LLMs show that LifeMem improves alignment with human data in terms of response distributions, overall and within-group diversity, and patterns of within-person response change across life stages. These findings highlight the value of longitudinal life-event memory for constructing more faithful and dynamically evolving social agents.
