研究长时任务中用户说服如何影响AI代理行为，发现事前信念干预显著改变其搜索习惯。
Understanding Persuasion in Long-Running Agents
- 区分任务中与任务前的说服干预，构建行为中心评估框架
- 事前设定信念使代理搜索次数减少26.9%，访问来源少16.9%
- 揭示信念传播效应，适合关注代理可塑性与行为评估的研究者
现代AI代理越来越多地结合对话交互与自主任务执行（如编程和网络调研），引发一个自然问题：当参与长期任务的代理受到用户说服时会发生什么？然而，由于长时任务行为具有噪声大、复现成本高的特点，且尚不清楚长期执行独有的挑战，研究该现象颇具难度。本文研究信念层面干预如何影响下游任务行为，这一现象称为说服传播。我们提出一种以行为为中心的评估框架，区分任务中与任务前的说服应用。在网页调研和编程任务中，发现实时说服仅产生微弱且不一致的行为影响；而当任务开始时明确指定信念状态，信念预设代理平均比中性预设代理减少26.9%的搜索次数，访问唯一来源减少16.9%。结果表明，即使在前期互动中，说服仍能影响代理行为，推动对代理系统进行行为级评估。
原文摘要 · Abstract (English)
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 exposed to user persuasion? Yet studying this possibility is challenging because long-running agent behavior is noisy and costly to reproduce, and it remains unclear which unique challenges emerge only in extended task execution. We study how belief-level intervention can influence downstream task behavior, a phenomenon we name 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.
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。