We introduce an approach to evaluate language model (LM) agency using negotiation games. This approach better reflects real-world use cases and addresses some of the shortcomings of alternative LM benchmarks. Negotiation games enable us to study multi-turn, and cross-model interactions, modulate complexity, and side-step accidental evaluation data leakage. We use our approach to test six widely used and publicly accessible LMs, evaluating performance and alignment in both self-play and cross-play settings. Noteworthy findings include: (i) only closed-source models tested here were able to complete these tasks; (ii) cooperative bargaining games proved to be most challenging to the models; and (iii) even the most powerful models sometimes "lose" to weaker opponents

翻译：我们提出了一种利用谈判游戏评估语言模型（LM）能动性的方法。该方法能更好地反映实际应用场景，并弥补其他语言模型基准测试的一些不足。谈判游戏使我们能够研究多轮交互和跨模型交互，调节复杂度，并避免意外评估数据泄露。我们利用该方法测试了六种广泛使用且可公开访问的语言模型，评估了它们在自对弈和跨模型对弈中的性能与对齐表现。值得关注的发现包括：（i）本文测试的仅闭源模型能够完成这些任务；（ii）合作谈判游戏对模型最具挑战性；（iii）即使是最强大的模型有时也会“输给”较弱的对手。