Modern AI agents increasingly combine conversational interaction with autonomous task execution, such as coding and web research, raising a natural question: what happens when an agent engaged in long-horizon tasks is subjected to user persuasion? We study how belief-level intervention can influence downstream task behavior, a phenomenon we name \emph{persuasion propagation}. We introduce a behavior-centered evaluation framework that distinguishes between persuasion applied during or prior to task execution. Across web research and coding tasks, we find that on-the-fly persuasion induces weak and inconsistent behavioral effects. In contrast, when the belief state is explicitly specified at task time, belief-prefilled agents conduct on average 26.9\% fewer searches and visit 16.9\% fewer unique sources than neutral-prefilled agents. These results suggest that persuasion, even in prior interaction, can affect the agent's behavior, motivating behavior-level evaluation in agentic systems.

翻译：现代人工智能智能体日益将对话式交互与自主任务执行（如编程和网络研究）相结合，这引发了一个自然问题：当执行长期任务的智能体受到用户说服时会发生什么？我们研究了信念层面的干预如何影响下游任务行为，这一现象我们称之为\emph{说服传播}。我们引入了一个以行为为中心的评价框架，区分在任务执行期间或之前施加的说服。在网络研究和编程任务中，我们发现实时说服仅能引发微弱且不一致的行为效应。相比之下，当在任务开始时明确指定信念状态时，信念预填充智能体比中性预填充智能体平均减少26.9%的搜索次数并访问16.9%更少的独立信息源。这些结果表明，即使在先前的交互中施加说服，也能影响智能体的行为，这为智能体系统中的行为层面评估提供了依据。