PulseAugur
中
实时 09:57:37
English(EN) Triadic Werewolf: A Jester Role for Multi-Hop Theory of Mind in LLMs

新的“Triadic Werewolf”游戏测试大语言模型的多智能体推理能力

研究人员开发了一种新的多跳心智理论评估方法,名为 Triadic Werewolf,用于评估大语言模型。该游戏扩展了传统的 Werewolf 游戏,引入了一个具有相反获胜条件的“弄臣”(Jester)角色,要求模型在三个对立的效用函数之间进行推理。在对 GPT-4.1、DeepSeek-V3.1 和 Llama 3.3 70B Instruct 的测试中,“弄臣”角色非常成功,赢得了 60-70% 的游戏,而狼人阵营的胜率很少超过 20%。值得注意的是,GPT-4.1 在此方面表现不佳,经常过早地投票淘汰“弄臣”,这表明其在该复杂的多智能体推理场景中存在弱点。 AI

影响 这种新的评估方法可以揭示大语言模型在当前基准测试之外的更深层次的推理能力。

排序理由 该集群包含一篇详细介绍大语言模型新评估方法的论文。

在 arXiv cs.MA (Multiagent) 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的“Triadic Werewolf”游戏测试大语言模型的多智能体推理能力

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群包含一篇详细介绍大语言模型新评估方法的论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
103 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Avni Mittal ·

    三元狼人:大型语言模型多跳心智理论中的小丑角色

    arXiv:2606.27909v1 Announce Type: cross Abstract: Theory-of-mind evaluations of large language models typically use dyadic social-deduction games, where every observable cue points to a single hidden side, so a model with strong language priors can score well without ever simulat…

  2. arXiv cs.MA (Multiagent) TIER_1 English(EN) · Avni Mittal ·

    三元狼人:大型语言模型多跳心智理论中的小丑角色

    Theory-of-mind evaluations of large language models typically use dyadic social-deduction games, where every observable cue points to a single hidden side, so a model with strong language priors can score well without ever simulating opponents' incentives. We extend the Werewolf …