LLM 多智能体更易羊群失控：Stanford/Cornell Music Lab 复现，强影响下分歧均值 +65%
LLM 多智能体更易羊群失控：Stanford/Cornell Music Lab 复现，强影响下分歧均值 +65%
View PDF HTML (experimental) Abstract: Large language models (LLMs) increasingly operate in multi-agent systems where they collaborate by responding to others' choices, creating endogenous feedback loops with vulnerability to social influence, herding behavior and runaway...
Stanford/Cornell Music Lab 复现 (arXiv:2610.30769)
“View PDF HTML (experimental) Abstract: Large language models (LLMs) increasingly operate in multi-agent systems where they collaborate by re”
Abstract:Large language models (LLMs) increasingly operate in multi-agent systems where they collaborate by responding to others' choices, creating endogenous feedback loops with vulnerability to social influence, herding behavior and runaway cascades. Following the design of the classic Music Lab experiment, we tested this vulnerability in large populations of LLM agents that recommended unfamiliar songs, with or without exposure to cumulative recommendation counts. Exposure led to runaway cascades that generated extreme and unpredictable collective recommendations increasingly divergent from a song's intrinsic appeal. Compared to humans, LLM populations were generally far more susceptible to herding behavior, and unlike humans, LLM cascades were less able to self-correct. This vulnerability has implications for multi-agent collaboration in recommender systems, automated evaluation, complex problem-solving, and unauthorized conspiracies.
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.30769 [cs.AI] |
| (or arXiv:2610.30769v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.30769 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Farnoosh Hashemi [view email]
[v1]
Thu, 22 Oct 2026 05:42:55 UTC (12,860 KB)
Source: Agent Control Flash News · arxiv.org
Related Products & Analysis
Cursor Agent 架构全景拆解：从影子工作区到多文件推演引擎
全面剖析 Cursor 在 Agent 模式下的底层技术实现，解析影子分支隔离、LSP 上下文剪枝以及预测性补全的核心架构细节与工程实践经验。
Vercel v0 推出全新多 Agent 协作画布与实时全栈部署预览
动态速评：v0 正在从单一组件生成器演进为全栈应用搭建协作台，尤其是与 Neon/Postgres 的直连极大降低了全栈原型验证成本。