超越对话的心智理论与说服：通过规划与行动评估LLMs诱导信念状态的能力
Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action
AI总结：
提出非对话式规划心智理论（NCP-ToM）框架，评估LLMs通过行动而非对话诱导他人信念状态的能力，发现GPT-5在80%任务中优于人类，但鲁棒性不足。
摘要：
大型语言模型（LLMs）的心智理论（ToM）基准通常依赖于被动问答形式，但随着LLMs以越来越具代理性和自主性的形式部署，需要新的评估方法。在本文中，我们评估了代理通过采取行动而非使用对话说服来诱导其他代理特定信念状态的能力，我们将这种能力称为非对话式规划心智理论（NCP-ToM）。NCP-ToM对于许多代理用例（包括用户-助手交互和教学环境）可能至关重要，但也可能带来操纵或错误信息的风险。使用新颖的框架NCP-ExploreToM，我们颠覆了传统的任务结构，为模型提供一组信念状态目标，并要求它们移动物体或将角色引导到房间中来实现目标。我们评估了六个前沿模型，包括GPT-5、Gemini 2.5 Pro和Claude 4系列，以及一组人类参与者，在600个任务实例上进行测试。GPT-5在代理设置中成功完成了约80%的任务，是唯一在任务上表现优于人类参与者的模型，但在不同情境下的鲁棒性仍不如人类。我们还发现，所有模型（如人类一样）在诱导真实信念状态的任务上比诱导错误信念状态的任务表现更好，这对对齐工作是一个积极信号。这些发现突显了LLMs在非对话式任务完成中新兴的社会推理能力，并强调了代理评估对于理解自主社会代理的安全性和对齐的必要性。
英文摘要：
Theory of Mind (ToM) benchmarks for Large Language Models (LLMs) typically rely on passive question-answering formats, but the deployment of LLMs in increasingly agentic and autonomous forms demands new evaluations. In this paper we evaluate an agent's ability to induce specific belief states in other agents by taking actions rather than using conversational persuasion, a capability we call Non-Conversational Planning ToM (NCP-ToM). NCP-ToM is likely to be essential for many agent use-cases, including within user-assistant interactions and pedagogical contexts, but may also present manipulation or misinformation risks. Using a novel framework, NCP-ExploreToM, we subvert the conventional task structure by providing models with a set of belief state goals and requiring them to move objects or direct characters into rooms to achieve their goals. We evaluated six frontier models, including GPT-5, Gemini 2.5 Pro and the Claude 4 series, and a cohort of human participants, across 600 task instances. GPT-5 was successful on approximately 80% of tasks in the agentic setting, and was the only model to outperform human participants on our task, but was still less robust than humans across contexts. We additionally found that all models, like humans, performed better on tasks inducing true belief states than false belief states, which is a positive signal for alignment efforts. These findings highlight emerging social-reasoning capabilities in LLMs for non-conversational task completion and underscore the necessity of agentic evaluations for understanding the safety and alignment of autonomous social agents.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
