AI agents会盲目跟风，历史数据如何呈现影响其集体决策。
How AI Agents Follow the Herd of AI? Network Effects, History, and Machine Optimism
- 用大模型代理模拟重复决策，操控价格走势与网络效应强度。
- 有序历史让弱网络效应下部分收敛，强效应时引发持续乐观误判。
- 随机历史彻底破坏收敛，凸显时间连贯性对AI推理的关键作用。
理解多智能体框架中的决策机制对于分析网络效应驱动情境下的战略互动至关重要。本研究探讨了在个体收益依赖于同伴参与的网络效应博弈中，AI代理如何行动——这一情境虽在现实世界普遍存在，却在多智能体系统中长期被忽视。我们提出一种基于大语言模型（LLM）代理的新工作流程，在重复决策场景中系统性地操纵价格轨迹（固定、上升、下降、随机）和网络效应强度。关键发现包括：第一，缺乏历史数据时，代理无法推断均衡；第二，有序的历史序列（如价格持续上升）可在弱网络效应下实现部分收敛，但强网络效应会引发持久的“AI乐观”——即使证据相反，代理仍高估参与度；第三，随机历史完全破坏收敛，表明时间连贯性对LLM推理具有决定性影响，而人类不受此限。这些结果揭示了一个范式转变：在AI介导的系统中，均衡结果不仅取决于激励设计，更取决于历史数据的编排方式，这是人类无法做到的。
原文摘要 · Abstract (English)
Understanding decision-making in multi-AI-agent frameworks is crucial for analyzing strategic interactions in network-effect-driven contexts. This study investigates how AI agents navigate network-effect games, where individual payoffs depend on peer participatio--a context underexplored in multi-agent systems despite its real-world prevalence. We introduce a novel workflow design using large language model (LLM)-based agents in repeated decision-making scenarios, systematically manipulating price trajectories (fixed, ascending, descending, random) and network-effect strength. Our key findings include: First, without historical data, agents fail to infer equilibrium. Second, ordered historical sequences (e.g., escalating prices) enable partial convergence under weak network effects but strong effects trigger persistent "AI optimism"--agents overestimate participation despite contradictory evidence. Third, randomized history disrupts convergence entirely, demonstrating that temporal coherence in data shapes LLMs' reasoning, unlike humans. These results highlight a paradigm shift: in AI-mediated systems, equilibrium outcomes depend not just on incentives, but on how history is curated, which is impossible for human.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。