PulseAugur
中
实时 06:55:24
English(EN) Communication Shapes Collective Inference in Self-Adapting LLM Societies: Evidence from Mafia

“杀手游戏”中的LLM代理展示了沟通在集体推理中的复杂作用

研究人员利用“杀手游戏”作为试验场,探索了沟通策略如何影响自适应大型语言模型社会中的集体推理。研究发现,与沉默相比,同时广播沟通在各种规模和组成的群体中都能提高识别对手的能力。然而,随着群体规模的扩大和时间的推移,这种优势会减弱,因为代理会调整它们的策略,有时会导致比沉默群体更差的表现。由代理重写和继承策略笔记驱动的适应过程表明,沟通的价值与其产生的演变信号交织在一起。 AI

影响 展示了沟通协议和代理适应如何影响LLM社会中的集体决策。

排序理由 学术论文,详细介绍了关于LLM代理行为的模拟研究。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.MA (Multiagent) 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

“杀手游戏”中的LLM代理展示了沟通在集体推理中的复杂作用

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
Tool
学术论文,详细介绍了关于LLM代理行为的模拟研究。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
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
2 days old
Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.MA (Multiagent) TIER_1 English(EN) · Joey Xiao ·

    通信塑造自适应LLM社会中的集体推理:来自“马法”的证据

    When does communication help a group identify hidden adversaries, and how does its value change as the group adapts? In Mafia, an informed minority hides inside an uninformed majority whose only evidence is open play. The zero-information game, where each day's vote eliminates a …