Metraipolis › archive › dc_292ed2f15737

Financial Fragility in Societies of LLM Agents: Coordination Failures and Stabilizing Mechanisms — arXiv:2609.30940

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30940
License (as archived)
CC0-1.0
Archived
2026-10-08T01:38:27.339Z
SHA-256 of the archived text
539f5b8be42ef14ad7cce52aa8848dfe99c7082e2becc5af228c2ae01a3c91b6
Stable URL of this page
https://metraipolis.com/documento/dc_292ed2f15737

How to cite

Financial Fragility in Societies of LLM Agents: Coordination Failures and Stabilizing Mechanisms — arXiv:2609.30940 — arXiv (en), https://arxiv.org/abs/2609.30940 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_292ed2f15737 (Metraipolis archive dc_292ed2f15737, sha256 539f5b8be42ef14ad7cce52aa8848dfe99c7082e2becc5af228c2ae01a3c91b6)
BibTeX
@misc{dc292ed2f15737,
  title = {Financial Fragility in Societies of LLM Agents: Coordination Failures and Stabilizing Mechanisms — arXiv:2609.30940},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30940},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_292ed2f15737; sha256 539f5b8be42ef14ad7cce52aa8848dfe99c7082e2becc5af228c2ae01a3c91b6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30940. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Individually protective decisions can produce avoidable collective failures. As large language model (LLM) agents take on greater roles in financial decision-making, financial AI safety must therefore be considered not only at the level of individual agents, but also at the level of the systems they jointly create. We study this problem with FRAIL, a controlled experimental framework that places LLM agents in three dynamic financial environments---bank runs, debt rollover, and reward crowdfunding---where agents' decisions reshape the financial conditions faced by others. Across seven leading LLMs, we find widespread collective fragility even when no agent is instructed to destabilize the system: 77\% of baseline bank-run episodes and 83\% of debt-rollover episodes end in failure. We then compare three interaction mechanisms based on compensated commitments, centralized commitment agreements, and participant-led coalitions. All three improve aggregate outcomes, but no single mechanism performs best across all financial structures. Across mechanisms, successful stabilization shares a common temporal pattern: broad commitment forms early, before defensive behavior becomes self-reinforcing. Our findings show that individually capable agents do not automatically form safe financial systems, highlighting system-level evaluation and interaction design as central problems for financial AI safety. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; General Finance (q-fin.GN).
Pagina del lavoro: https://arxiv.org/abs/2609.30940 — 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 2026-10-08T01:12:14.313Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).