A Dual-Process Perspective on Nudge Susceptibility in LLM-Based GUI Agents
Haya Halimeh and colleagues run a randomized online shopping experiment with 3,600 agents and 21,600 simulations across six frontier models to test whether LLM GUI agents are susceptible to digital nudges.
Ask this paper
Both nudge types land. Agents are influenced by automatic Type 1 nudges such as defaults and by reflective Type 2 nudges such as social influence.
Reasoning moves the two in opposite directions. Extensive reasoning reduces susceptibility to default nudges while increasing susceptibility to social influence nudges.
Reasoning redirects rather than protects. The total effect of choice architecture persists; only the route through which it operates changes, which is the finding that undercuts reasoning as a mitigation.
The redirection scales with model size. Exploratory analysis shows the pattern is systematically structured by model scale, so it is not an artifact of one provider.
Interface design becomes a governance concern. Organizations delegating purchases to agents inherit the nudges built into the interfaces those agents operate.
Abstract
LLM-based GUI agents increasingly act on behalf of users in digital environments that were designed with human users in mind. These graphical user interfaces were designed to support, but also deliberately steer, the behaviour and decisions of users. While behavioural biases in the textual outputs of LLMs are well-documented, far less is known about how such influence operates when models act as agents that perceive interfaces and execute decisions---and, in particular, whether the reasoning capabilities increasingly built into these agents make them more robust to it. Drawing on Dual-Process Theory, we empirically investigate whether LLM-based GUI agents are susceptible to automatic (Type 1) and reflective (Type 2) digital nudges, and how their reasoning configuration moderates this susceptibility. In a randomized online shopping experiment with 3,600 agents and a total of 21,600 simulations across six frontier models from three providers, we found that agents were vulnerable to both nudge types. Crucially, the reasoning configuration moderated these effects in opposing directions, reducing susceptibility to automatic default nudges while heightening it to reflective social influence nudges. Extensive reasoning therefore did not make agents more robust but redirected the route through which choice architecture takes effect. Exploratory analysis further showed this redirection to be systematically structured by model scale. Beyond establishing nudge susceptibility as a behavioural property of agentic AI, the study positions interface design as a governance concern for organizations that delegate decisions to autonomous agents.