Human Trust of AI Agents
Interesting research: “Humans expect rationality and cooperation from LLM opponents in strategic games.”
Abstract: As Large Language Models (LLMs) integrate into our social and economic interactions, we need to deepen our understanding of how humans respond to LLMs opponents in strategic settings. We present the results of the first controlled monetarily-incentivised laboratory experiment looking at differences in human behaviour in a multi-player p-beauty contest against other humans and LLMs. We use a within-subject design in order to compare behaviour at the individual level. We show that, in this environment, human subjects choose significantly lower numbers when playing against LLMs than humans, which is mainly driven by the increased prevalence of ‘zero’ Nash-equilibrium choices. This shift is mainly driven by subjects with high strategic reasoning ability. Subjects who play the zero Nash-equilibrium choice motivate their strategy by appealing to perceived LLM’s reasoning ability and, unexpectedly, propensity towards cooperation. Our findings provide foundational insights into the multi-player human-LLM interaction in simultaneous choice games, uncover heterogeneities in both subjects’ behaviour and beliefs about LLM’s play when playing against them, and suggest important implications for mechanism design in mixed human-LLM systems.
Subscribe to comments on this entry
Clive Robinson • April 16, 2026 6:37 AM
@ Bruce, ALL,
The title,
Might be a factual statement…
But any person who “expects rationality and cooperation” from an LLM Opponent, clearly does not understand the way they work.
And how they can be biased easily to appear to act one way whilst actually acting in another way.
Thus the old,
“To err is human”
Appears to be the true message.
Based in part on our desire to form communities where implicit trust is in effect a foundation stone of society.