Metraipolis › archive › dc_bf68333440be

GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent Communities — arXiv:2608.17665

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.17665
License (as archived)
CC0-1.0
Archived
2026-10-18T14:28:46.586Z
SHA-256 of the archived text
68b6bfb0b215fa241ec4c42dadb548d1672baa3097cf56f104ffe302fe49da99
Stable URL of this page
https://metraipolis.com/documento/dc_bf68333440be

How to cite

GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent Communities — arXiv:2608.17665 — arXiv (en), https://arxiv.org/abs/2608.17665 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf68333440be (Metraipolis archive dc_bf68333440be, sha256 68b6bfb0b215fa241ec4c42dadb548d1672baa3097cf56f104ffe302fe49da99)
BibTeX
@misc{dcbf68333440be,
  title = {GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent Communities — arXiv:2608.17665},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.17665},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf68333440be; sha256 68b6bfb0b215fa241ec4c42dadb548d1672baa3097cf56f104ffe302fe49da99},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17665. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-driven agents can autonomously exchange opinions on online platforms and form communities. Such agent-operated social platforms raise a new security concern: attackers may manipulate agents to induce group polarization. Existing methods manipulate agent prompts or construct echo chambers, both of which are difficult to realize in practice. We therefore formulate a new threat, Memory-Mediated Polarization Cascade, which uses agent memory as a persistence channel and public discussion as a propagation channel. This threat contains three stages. During exposure and memory retention, the attacker exposes a small set of target agents to arguments that reinforce their respective stated stances. The targets' memory systems then process and retain these arguments. During retrieval and reproduction, a shared stance-neutral discussion cues the targets to retrieve and reproduce their respective retained arguments. During iterative propagation, untreated agents influenced by the reproduced arguments restate and spread them. We instantiate this threat in GraphWake with three components: (i) stance-support argumentation knowledge graphs construct knowledge-based arguments; (ii) axiom-oriented triple selection distills them for reliable retention and reproduction; and (iii) stance-neutral memory cueing triggers concurrent retrieval and reproduction, initiating propagation. Experiments across multiple discussions and memory systems show that GraphWake substantially increases group polarization. These findings reveal a community-level polarization risk.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.17665 — 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 2026-10-18T14:27:54.291Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).