验证所需：信息可信度对AI说服力的影响
Verification Required: The Impact of Information Credibility on AI Persuasion
AI总结：
研究提出MixTalk游戏模型，通过验证与不可验证声明的结合，探讨信息可信度对AI说服力的影响，并提出TOPD方法提升接收者鲁棒性。
摘要：
由大型语言模型（LLMs）驱动的智能体正越来越多地应用于通信影响高风险决策的领域，这使得对战略性沟通的系统理解变得至关重要。以往的研究大多关注不可验证的廉价谈话或完全可验证的披露，未能捕捉到信息具有概率可信度的真实领域。我们引入了MixTalk，一种针对LLM之间交互的战略沟通游戏，该游戏建模了信息可信度。在MixTalk中，发送者智能体战略性地结合可验证和不可验证的声明来传达私人信息，而接收者智能体则将有限的预算用于昂贵的验证，并从先前信念、声明和验证结果中推断出底层状态。我们评估了最先进的LLM智能体在三个现实部署场景中的大规模锦标赛，揭示了它们在推理信息可信度和塑造这些互动的显式行为方面的优缺点。最后，我们提出了Tournament Oracle Policy Distillation（TOPD），一种离线方法，通过交互日志提炼锦标赛Oracle策略，并在推理时上下文部署。我们的结果表明，TOPD显著提高了接收者对说服的鲁棒性。
英文摘要：
Agents powered by large language models (LLMs) are increasingly deployed in settings where communication shapes high-stakes decisions, making a principled understanding of strategic communication essential. Prior work largely studies either unverifiable cheap-talk or fully verifiable disclosure, failing to capture realistic domains in which information has probabilistic credibility. We introduce MixTalk, a strategic communication game for LLM-to-LLM interaction that models information credibility. In MixTalk, a sender agent strategically combines verifiable and unverifiable claims to communicate private information, while a receiver agent allocates a limited budget to costly verification and infers the underlying state from prior beliefs, claims, and verification outcomes. We evaluate state-of-the-art LLM agents in large-scale tournaments across three realistic deployment settings, revealing their strengths and limitations in reasoning about information credibility and the explicit behavior that shapes these interactions. Finally, we propose Tournament Oracle Policy Distillation (TOPD), an offline method that distills tournament oracle policy from interaction logs and deploys it in-context at inference time. Our results show that TOPD significantly improves receiver robustness to persuasion.
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。
