Metraipolis › archive › dc_571d8b20debd
LLM Multi-Agent Systems Are Vulnerable to Herding and Runaway Cascades — arXiv:2610.30769
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.30769
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T21:32:11.634Z
- SHA-256 of the archived text
54206ff80eeaf3d018b17f663958dd32d44d643c44d89c313811397b443846c5- Stable URL of this page
https://metraipolis.com/documento/dc_571d8b20debd
How to cite
LLM Multi-Agent Systems Are Vulnerable to Herding and Runaway Cascades — arXiv:2610.30769 — arXiv (en), https://arxiv.org/abs/2610.30769 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_571d8b20debd (Metraipolis archive dc_571d8b20debd, sha256 54206ff80eeaf3d018b17f663958dd32d44d643c44d89c313811397b443846c5)
BibTeX
@misc{dc571d8b20debd,
title = {LLM Multi-Agent Systems Are Vulnerable to Herding and Runaway Cascades — arXiv:2610.30769},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.30769},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_571d8b20debd; sha256 54206ff80eeaf3d018b17f663958dd32d44d643c44d89c313811397b443846c5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30769. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2610.30769 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-25T21:24:47.952Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).