Metraipolis › archive › dc_c1b4555bb4cd
Warned alike, AI agents avoid the less-crowded road while people take it — arXiv:2609.30883
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30883
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T01:39:34.829Z
- SHA-256 of the archived text
71a7b5b010892e6b82f03a2fa973a4e962e1d3b477794424b9e171b2d832ca1e- Stable URL of this page
https://metraipolis.com/documento/dc_c1b4555bb4cd
How to cite
Warned alike, AI agents avoid the less-crowded road while people take it — arXiv:2609.30883 — arXiv (en), https://arxiv.org/abs/2609.30883 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c1b4555bb4cd (Metraipolis archive dc_c1b4555bb4cd, sha256 71a7b5b010892e6b82f03a2fa973a4e962e1d3b477794424b9e171b2d832ca1e)
BibTeX
@misc{dcc1b4555bb4cd,
title = {Warned alike, AI agents avoid the less-crowded road while people take it — arXiv:2609.30883},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30883},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c1b4555bb4cd; sha256 71a7b5b010892e6b82f03a2fa973a4e962e1d3b477794424b9e171b2d832ca1e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30883. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI agents built on a few shared models increasingly act for many people. A shared forecast about others can align their choices and change how scarce capacity is allocated. We tested this feedback in a two-road congestion game. Adding one sentence warning that others might follow a routing tip made populations of 50 GPT agents crowd one road while avoiding the nearly empty alternative. Average travel time rose from 64 to 95 min, although any crowded-road agent could have saved 69 min by switching alone. The warning discouraged the very move it predicted. The pattern persisted for 100 rounds. Two other model families shifted the same way without locking onto one road. Twelve all-human groups (240 participants) stayed near balance under numerical reports or the tip and warning. In 24 mixed groups with a further 240 participants, imbalance grew with the share of agents in the registered analysis, while people increasingly took the road the agents avoided. Collective costs stayed below the allagent reference, but with 15 agents and 5 humans, agent seats averaged 80 min, compared with 44 min for human seats. Shared forecasts can thus sustain collective inefficiency among similar agents. A better group average can also hide an unequal burden. Evaluations of AI agents that share resources should test populations, treat messages as interventions and report who bears the costs. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI). Categorie arXiv: Physics and Society (physics.soc-ph) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.30883 — 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 2026-10-08T01:12:14.494Z 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).