arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.20059cs.AI
收藏

交互戏剧:大规模LLM代理互动的案例

Interaction Theater: A case of LLM Agents Interacting at Scale

Sarath Shekkizhar, Adam Earle

AI总结:

研究发现大规模LLM智能体互动表面活跃但实质空洞,需设计协调机制以促进有效交流。

摘要:

随着多智能体架构和智能体间协议的普及,一个根本性问题浮现:当自主LLM智能体大规模互动时,实际上发生了什么?我们通过Moltbook的数据进行了实证研究,该平台是一个仅由AI智能体构成的社会平台,拥有800,000条帖子、350万条评论和78,000个智能体资料。我们结合词汇度量(Jaccard特异性)、基于嵌入的语义相似性以及LLM作为评判者的验证来表征智能体互动质量。我们的发现表明,智能体生成的文本多样且结构良好,表面呈现出活跃讨论的表象,但实质内容大多缺失。具体而言,尽管大多数智能体(67.5%)在不同上下文中会变化输出,但65%的评论与它们所出现的帖子没有可区分的内容词汇,且额外评论的信息增益迅速衰减。基于LLM评判的指标将主导评论类型分类为垃圾信息(28%)和无关内容(22%)。基于嵌入的语义分析证实,词汇通用的评论也是语义通用的。智能体很少进行线程式对话(仅5%的评论),更倾向于独立的顶层回应。我们讨论了多智能体互动设计的启示,认为协调机制必须明确设计;否则,即使拥有大量有能力的智能体,也会产生平行输出而非有效交流。

英文摘要:

As multi-agent architectures and agent-to-agent protocols proliferate, a fundamental question arises: what actually happens when autonomous LLM agents interact at scale? We study this question empirically using data from Moltbook, an AI-agent-only social platform, with 800K posts, 3.5M comments, and 78K agent profiles. We combine lexical metrics (Jaccard specificity), embedding-based semantic similarity, and LLM-as-judge validation to characterize agent interaction quality. Our findings reveal agents produce diverse, well-formed text that creates the surface appearance of active discussion, but the substance is largely absent. Specifically, while most agents ($67.5\%$) vary their output across contexts, $65\%$ of comments share no distinguishing content vocabulary with the post they appear under, and information gain from additional comments decays rapidly. LLM judge based metrics classify the dominant comment types as spam ($28\%$) and off-topic content ($22\%$). Embedding-based semantic analysis confirms that lexically generic comments are also semantically generic. Agents rarely engage in threaded conversation ($5\%$ of comments), defaulting instead to independent top-level responses. We discuss implications for multi-agent interaction design, arguing that coordination mechanisms must be explicitly designed; without them, even large populations of capable agents produce parallel output rather than productive exchange.

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。

↑