Warned alike, AI agents avoid the less-crowded road while people take it
Abstract
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.
Related
- Why Emission Spectral Profile of Diverse Fluoro-phores Look Alike with Thick Polymer Overlayers?
- Mechano-chemical control of enzymatic activity in crowded environments
- Dynamical and conformational behavior of a polymer in a crowded solution
- Macroscopic freezing of a vector Gaussian free field conditioned to avoid a ball
- Attention Is All You Need (to Avoid Spurious Oscillations)
BibTeX
@misc{ezaki2026warned,
title = {{Warned alike, AI agents avoid the less-crowded road while people take it}},
author = {Takahiro Ezaki and Naoto Imura and Katsuhiro Nishinari},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.30883},
eprint = {2609.30883},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.30883},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Warned alike, AI agents avoid the less-crowded road while people take it
AU - Takahiro Ezaki
AU - Naoto Imura
AU - Katsuhiro Nishinari
PY - 2026
DA - 2026/09/25
PB - arXiv
DO - 10.48550/arxiv.2609.30883
UR - https://arxiv.org/abs/2609.30883
AB - 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.
ER -