Metraipolis › archive › dc_98dddeebf90a

But How Would AI Agents Run a Town's Economy? — arXiv:2609.11108

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.11108
License (as archived): CC0-1.0
Archived: 2026-10-16T05:20:28.273Z
SHA-256 of the archived text: daad79b80cfbd4a25c3103c8cdad00033b7b741c8f0c876c688ea38d2fbba873
Stable URL of this page: https://metraipolis.com/documento/dc_98dddeebf90a

How to cite

But How Would AI Agents Run a Town's Economy? — arXiv:2609.11108 — arXiv (en), https://arxiv.org/abs/2609.11108 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_98dddeebf90a (Metraipolis archive dc_98dddeebf90a, sha256 daad79b80cfbd4a25c3103c8cdad00033b7b741c8f0c876c688ea38d2fbba873)

BibTeX

@misc{dc98dddeebf90a,
  title = {But How Would AI Agents Run a Town's Economy? — arXiv:2609.11108},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11108},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_98dddeebf90a; sha256 daad79b80cfbd4a25c3103c8cdad00033b7b741c8f0c876c688ea38d2fbba873},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11108. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We placed 100 memory-equipped large language model (LLM) agents in charge of a closed, money-conserving spatial economy on real Pokhara Lakeside geography (earning wages, running businesses, setting prices) and ran this multi-agent simulation for up to 26 simulated weeks, well past the 1-2 weeks typical of agent-society studies. Across 91 validated runs (2.44M agent decisions, 21.5B tokens), the money stops moving, in a specific and measurable way. A 12x tourist demand shock raises business revenue 4.62x ($p<0.001$), which we decompose exactly into a 1.50x extensive margin (more businesses trading) and a 3.07x intensive margin (more revenue each). Monetary transmission stops there. Wages move 1.03x ($p=0.42$); 0.3% of 3,981 menu items are ever repriced ($p=0.47$). A randomized cash transfer (NPR 5,000 to 20 of 100 agents) shows the same pattern from the opposite direction: 96.7% is still held 311 pulses later, marginal propensity to consume 3-4% by two independent measures, indistinguishable from zero. The wealth distribution is consequently near-frozen at the horizon this literature uses ($\rho=0.964$ over 2 simulated weeks), but not frozen. $\rho$ falls to 0.832 at 12 weeks and 0.752 at 26, a horizon-dependence no short study can see. Matched ablations show which knob actually matters. Swapping the backing LLM moves every outcome we measure ($p=0.0039$); deleting agents' memory moves none of them detectably. A purely social tool fails 94-97% of the time across two model families, compared with ~96% success on economic tools, with no measurable shift away from it. Every headline number is verified twice, by a live validator and by an offline recomputation that reconciles each agent's wealth against its own signed transaction history, and we release the full run corpus for reanalysis.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA) ; Emerging Technologies (cs.ET).
Pagina del lavoro: https://arxiv.org/abs/2609.11108 — 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 2026-10-16T05:15:07.136Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).