Game of Phones：用博弈论引导 LLM 反制电话诈骗
Game of Phones: Harnessing Game Theory and LLMs in 'Bot Wars' to Counteract Phone Scams
想让 LLM 学会跟骗子周旋的可以看看：不用微调，靠博弈论加 300 段模拟对话，策略选择比基线更接近 Nash 均衡，代码和数据都开源了。
arXiv 论文提出一个博弈论框架，把诈骗者与反制者建模为双人博弈，让 LLM 通过上下文经验学习反诈策略，无需微调。实验覆盖 300 段模拟对话和三种 LLM 架构，以 Nash 均衡作为策略评估基准。自适应策略选择使学习行为比非自适应基线更接近 Nash 均衡 28.9-79.7%。团队同时发布了 300 段带回合级策略标签和效用分数的标注数据集与代码。
Game of Phones: Harnessing Game Theory and LLMs in 'Bot Wars' to Counteract Phone Scams
Phone scams impose substantial and growing costs on individuals and financial systems worldwide, yet existing countermeasures impose no resource cost on perpetrators. Strategic scam-baiting, in which automated agents engage scammers to deplete their operational capacity, offers a proactive alternative but requires dynamic strategy adaptation that static systems cannot provide. We introduce a game-theoretic framework enabling LLMs to learn effective counter-strategies through in-context experience without fine-tuning. The framework models scammer-baiter interactions as a two-player game with empirically grounded strategies and utility functions, using Nash equilibrium as a formal benchmark for evaluating learned behaviour. Across 300 simulated dialogues and three LLM architectures, adaptive strategy selection achieves 28.9-79.7% closer alignment to Nash equilibrium than non-adaptive baselines. The code and an annotated dataset of 300 dialogues with turn-level strategy labels and utility scores are released at https://github.com/nardinebasta/GameofPhones_/ .