塑造观点：量化自主多智能体LLM交互的心理影响
Shaping Opinion: Quantifying the Psychological Impact of Autonomous Multi-Agent LLM Interactions
浏览论文内容
中文总结 AI 辅助
本研究提出FORMS低延迟多智能体对话架构，通过实验发现高能力系统引发认知失稳与监管觉醒，并揭示真实性悖论，证明其能重塑人类信息处理。
中文摘要 AI 辅助
自然流畅的多智能体对话式人工智能正日益普及，从根本上改变了人机交互和人类信息处理方式。以往研究主要关注算法失败，而本研究则探讨算法能力对认知工效学和社会认知的影响。我们提出并评估了FORMS（多智能体模拟中的观点与修辞框架），这是一种用于空间中介人机对话的低延迟架构，由不同的基于LLM的人格和实时并发解决机制驱动。为了对其心理影响进行系统测试和评估，我们让一组青少年（n=120）和一组成人试点（n=25）接触了一场实时、有主持的合成辩论。我们的研究结果显示，接触高能力多智能体系统会引发“认知失稳”，瓦解用户先前的一致战略共识。同时，我们观察到由“常态悖论”驱动的“监管觉醒”：流畅的人机交互本质上增加了对外部监管的基线需求。此外，我们的试点研究表明存在“真实性悖论”：尽管了解生成式人工智能的风险，成人组参与者对合成辩论的真实性评分显著高于同等人类话语（Cohen's d=2.04）。在稳健的统计效应量支持下，本文贡献了FORMS架构和可复制的评估协议，阐明了高保真对话系统如何重塑人类信息处理。
英文摘要
Natural-sounding multi-agent conversational AI is increasingly deployed, fundamentally altering human-machine interaction and human information processing. While prior work largely focuses on algorithmic failure, this study investigates the cognitive ergonomics and socio-cognitive impact of algorithmic competence. We present and evaluate FORMS (Framework for Opinion and Rhetoric in Multi-agent Simulations), a low-latency architecture for spatially mediated human-machine dialogue, driven by distinct LLM-based personas and real-time concurrency resolution. To conduct a system test and evaluation of its psychological impact, we exposed an adolescent cohort (n=120) and an adult pilot group (n=25) to a live, moderated synthetic debate. Our findings reveal that exposure to highly competent multi-agent systems triggers "Cognitive Destabilization," fragmenting users' prior strategic consensus. Concurrently, we observe a "Regulatory Awakening" driven by the "Normality Paradox": fluid human-machine interactions inherently increase the baseline demand for external regulation. Furthermore, our pilot study suggests the presence of a "Truthfulness Paradox": despite understanding the risks of generative AI, participants in the adult cohort rated the synthetic debate as significantly more sincere than equivalent human discourse (Cohen's d=2.04). Supported by robust statistical effect sizes, this paper contributes the FORMS architecture and a replicable evaluation protocol, illustrating how high-fidelity conversational systems can reshape human information processing.
发表机构
- Universidad de La Laguna（拉各纳大学）
- French National Centre for Scientific Research (CNRS)（法国国家科学研究中心）
- Toulouse Institute of Computer Science Research (IRIT)（图卢兹计算机科学研究所以）
- Centre for European Policy Studies（欧洲政策研究中心）
机构由 AI 辅助整理，请以论文原文为准。
