Designing Adaptive Digital Nudging Systems with LLM-Driven Reasoning

Tiziano Santilli; Mina Alipour; Mahyar Tourchi Moghaddam

cs.SEApr 13, 2026

Designing Adaptive Digital Nudging Systems with LLM-Driven Reasoning

Authors: Tiziano Santilli, Mina Alipour, Mahyar Tourchi Moghaddam

Organizations: Mærsk Mc-Kinney Møller Instituttet, Syddansk Universitet, Odense, Denmark

Abstract

Digital nudging systems lack architectural guidance for translating behavioral science into software design. While research identifies nudge strategies and quality attributes, existing architectures fail to integrate multi-dimensional user modeling with ethical compliance as architectural concerns. We present an architecture that uses behavioral theory through explicit architectural decisions, treating ethics and fairness as structural guardrails rather than implementation details. A literature review synthesized 68 nudging strategies, 11 quality attributes, and 3 user profiling dimensions into architectural requirements. The architecture implements sequential processing layers with cross-cutting evaluation modules enforcing regulatory compliance. Validation with 13 software architects confirmed requirements satisfaction and domain transferability. An LLM-powered proof-of-concept in residential energy sustainability demonstrated feasibility through evaluation with 15 users, achieving high perceived intervention quality and measurable positive emotional impact. This work bridges behavioral science and software architecture by providing reusable patterns for adaptive systems that balance effectiveness with ethical constraints.

Figures & tables

Attribute	Definition	Ref
Acceptability	Degree to which users perceive a nudge as appropriate or desirable, considering social, cultural, moral standards	[ 11 ]
Awareness	Degree of user attention to the nudge. Tension exists: high transparency may trigger reactance, subliminal approaches raise ethical concerns	[ 11 ]
Effectiveness	Degree to which a nudge achieves its intended behavioral outcome	[ 19 ]
Fairness	Ensures systems address algorithm/data biases and cognitive/perceptual biases, providing equitable access. Includes GDPR, AI Act, DSA compliance	[ 13 ]
Healthfulness	Degree to which users perceive an item or choice to impact their health positively	[ 11 ]
Helpfulness	Degree to which users perceive nudges as assisting decision-making	[ 11 ]

TABLE I: Quality Attributes for Digital Nudging

ID	Requirement	Component	Derivation & References
Functional Requirements
FR1	Capture context and behavioral data	Context Tracker, Behavioral Collector	Context-awareness [ 22 ] , behavioral signals [ 23 , 5 ]
FR2	Determine cognitive mode	Cognitive Mode	Dual-process theory [ 5 , 6 ]
FR3	Detect behavioral stage	Behavioral Stage	Transtheoretical Model [ 24 , 5 ]
FR4	Estimate attention capacity	Attention Capacity	Cognitive load theory [ 6 , 21 ]
FR5	Generate diverse nudges	Nudge Generator	Strategy taxonomy [ 24 , 25 , 19 ]

TABLE II: Architectural Requirements with Literature Traceability

Decision	Details
AD1: Sequential Pipeline vs. Event-Driven Architecture
Decision	Three sequential layers with per-user session processing rather than event-driven publish-subscribe.
Rationale	Digital nudging requires deterministic reasoning chains where User Modeling completes before Strategy Optimization. Sequential processing ensures causal consistency, reasoning transparency, and provenance tracking.
Trade-offs	Gains —Clear provenance, easier debugging, compliance auditability (GDPR Article 22), simplified testing. Costs —No intra-user parallelization, increased per-user latency.
Alternatives	Event-driven with orchestration (rejected: excessive overhead), blackboard architecture (rejected: non-deterministic control flow), pipes-and-filters (rejected: unnecessary given sequential requirements).
AD2: Side-Mounted Evaluation vs. Embedded Validators

TABLE III: Architectural Decisions and Rationale

Characteristic	Category	N (%)
Experience	0–5 years	4 (30.8%)
	5–10 years	5 (38.5%)
	10–15 years	1 (7.7%)
	15+ years	3 (23.1%)
Domain	Healthcare	3 (23.1%)
	Automotive	4 (30.8%)

TABLE IV: Architectural Evaluators Demographics (N=13)

Architectural Quality
Requirement	Mean
Maintainability & Evolvability	4.62
Regulatory Compliance	4.69
Functional Requirements
Context/Behavioral Data (FR1)	4.54
Cognitive Mode (FR2)	4.62

TABLE V: Structured Questionnaire Results (Likert Scale 1-5)

Characteristic	Category	N (%)
Age	18–24	5 (33.3%)
	25–34	6 (40.0%)
	35–44	3 (20.0%)
	45+	1 (6.7%)
Gender	Male	8 (53.3%)
	Female	7 (46.7%)

TABLE VI: User Study Participant Demographics (N=15)

ID	Cognitive	Stage	Attn	Strategy
1	Analytical	Contemplation	High	Just-in-time
2	Intuitive	Pre-contempl.	High	Remind conseq.
3	Intuitive	Contemplation	High	Enable compar.
4	Intuitive	Action	High	Raise visibility
5	Intuitive	Contemplation	High	Just-in-time
6	Intuitive	Action	Medium	Just-in-time

TABLE VII: User Testing System Classifications (N=15)

Metric	Mean Value
Nudge Quality (1–5)	4.73 (SD=0.46)
Explanation Quality (1–5)	4.27 (SD=0.70)
Pre-Nudge Happiness	0.000170 (SD=0.000092)
Post-Nudge Happiness	0.000500 (SD=0.000213)
Happiness Increase	0.000330 (SD=0.000158)

TABLE VIII: User Evaluation Results

Software Architecture Design

See all 22 papers

A Dual-Process Perspective on Nudge Susceptibility in LLM-Based GUI Agents
Sep 17, 2026Haya Halimeh, Sascha Kaltenpoth, Kevin Bösch +1Dual-Process Reasoning GUI Agents
Information Systems, Paderborn University, Paderborn, Germany.
Architecture Without Architects: How AI Coding Agents Shape Software Architecture
Apr 5, 2026Phongsakon Mark Konrad, Tim Lukas Adam, Riccardo Terrenzi +1Software Architecture Design AI Coding Agents
Centre for Industrial Software, University of Southern Denmark, Alsion 2, Sønderborg, 6400, Denmark
CAPRA: Scaling Feedback on Software Architecture Deliverables with a Multi-Agent LLM System
Jun 17, 2026Marco Becattini, Niccolò Caselli, Matteo Minin +2Software Engineering Multi-Agent LLM Systems
Department of Information Engineering, University of Florence, Florence, Italy

Sep 17, 2026J/K move · Enter open · S save

A Dual-Process Perspective on Nudge Susceptibility in LLM-Based GUI Agents

Haya Halimeh, Sascha Kaltenpoth, Kevin Bösch, Oliver Müller

Information Systems, Paderborn University, Paderborn, Germany.

Dual-Process Reasoning GUI Agents Agentic Reasoning AI Agent Governance

Open paper AskPDF arXiv

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.

Abstract

Software Architecture Design

Explore similar work

A Dual-Process Perspective on Nudge Susceptibility in LLM-Based GUI Agents

Architecture Without Architects: How AI Coding Agents Shape Software Architecture

CAPRA: Scaling Feedback on Software Architecture Deliverables with a Multi-Agent LLM System