【论文速递】A Framework for Context Enrichment and Selective Robustness in LLM Social Agents

英文标题：A Framework for Context Enrichment and Selective Robustness in LLM Social Agents

arXiv编号：2611.06914
作者：Mattia Greiche, Reihaneh Rabbany, Maximilian Puelma Touzel
来源：arXiv
原文链接：https://arxiv.org/abs/2611.06914

中文摘要：
Researchers use large language models as agents in social simulations, where agents are prompted with observations and background information intended to shape their actions. Yet LLM agents have been shown to substantially change their behavior under meaning-preserving prompt variations, creating a validation problem for social simulation. One plausible hypothesis is that this brittleness reflects a lack of grounding and can be reduced by enriching the context provided to the agents. Whether richer context improves robustness remains unclear, in part because context richness and robustness are rarely defined in ways that support controlled comparisons. We address the first need with controlled context enrichment, a set of prompt substitution rules that systematically enriches distinct types of context: neutral padding, generic social background, descriptive decision grounding, and normative decision grounding. We address the second by introducing selective robustness as a validation criterion: insensitivity to meaning-preserving prompt variation combined with a directional response to decision-relevant changes in the social world. We demonstrate the framework in a Prisoner's Dilemma-like game, showing how it can be used to identify which forms of context enrichment produce more desirable and robust agent behavior. We find that these forms of enrichment produce distinct behavioral patterns that vary between the two models tested.

本文由华人空间 AI 论文助手自动抓取翻译，仅供学术交流。