cs.SEOct 25, 2026

Developer Task Delegation to LLMs and the Trust Factor: A Mixed Methods Study

Authors: Samuel Ferino, Rashina Hoda, John Grundy, Christoph Treude, Hashini Gunatilake

Organizations: Faculty of Information Technology, Monash University, Melbourne, Australia. · School of Computing and Information Systems, Singapore Management University, Singapore.

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

With the rise of Large Language Models (LLMs), software developers are presented with a powerful new approach: delegating software development tasks to LLMs. Existing studies have explored task delegation for a subset of tasks and factors. Critically, what tasks developers delegate to LLMs, to what extent, and why they delegate them, is not yet well understood. We explore these questions through 22 interviews and a survey with 160 software practitioners. Developers reported employing four modes of task delegation to LLMs: full delegation, partial delegation, self-delegation, and task avoidance. Drawing on our qualitative findings, we discuss the rationales behind these choices and explore how task difficulty, task risk, developer motivation, and trust appear to be associated with software development task delegation to LLMs. Our statistical analysis reveals that trust is a significant factor associated with task delegation to LLMs. Finally, we share actionable implications for human-AI collaboration in software research, and for software practitioners to make the most of their newly found powers of delegation.

Figures & tables

Fig. 1 : Overview of the mixed methods research.
Fig. 2 : Emergence of the category “ Task Delegation Modes ” from raw data → codes → concepts → category through constant comparison.
HypothesisGrounding
H1H_{1} : Difficulty →\rightarrow Delegation Mode (−)(-)Higher perceived task difficulty decreases delegation to LLMs
H2H_{2} : Risk →\rightarrow Delegation Mode (−)(-)Higher perceived risk of delegating a task reduces willingness to fully delegate
H3H_{3} : Motivation →\rightarrow Delegation Mode (−)(-)Higher intrinsic motivation to perform a task oneself reduces delegation
H4H_{4} : Trust →\rightarrow Delegation Mode (+)(+)Higher trust in LLM capability for a specific task increases willingness to delegate that task
TABLE I : Four hypotheses formulated from Interview data analysis.
Figure 4
Location# of ParticipantsRole# of Participants
Australasia10Software Eng.6
North America5Software Dev.5
Latin America4Data Analyst2
Asia2AI Engineer1
Europe1Others8
Domain# of ParticipantsDomain# of Participants
TABLE II : Interview Participant Demographics (Dev: Developer; Eng: Engineer; XT: Total Professional Software Development Experience; XTL: LLMs for SE Experience; CLIP: Company’s LLM Policy).
Location# of ParticipantsRole# of Participants
Europe66Software Eng.49
North America35Software Dev.49
Asia23Web Dev.12
Latin America20Frontend Dev.8
Australasia8Cloud Eng.5
Africa8Other37
TABLE III : Survey Participants Demographics.
Fig. 3 : Task delegation modes (Interview findings).
Fig. 4 : Distribution of task delegation modes ( Survey findings; Del.: Fully and Partially Delegated).
Fig. 5 : Emerging factors across tasks. Task difficulty, perceived risk, developer motivation, and developer trust metrics vary from 0 to 4, while task delegation modes range from 0 to 3 (0: Task Avoidance; 1: Self-Delegation; 2: Partial Delegation; 3: Full Delegation).
FactorsStage 1
(No Del. vs. Del.)Stage 2
(Partial vs. Full)Empirical Finding
Difficulty ( H1H_{1} )β=−0.15\beta=-0.15
p=0.21p=0.21β=−0.08\beta=-0.08
p=0.55p=0.55Not Supported
Risk ( H2H_{2} )β=0.15\beta=0.15
TABLE IV : Sequential binary mixed-effects logistic regression model results for (1) Adoption stage (N=857) and (2) Autonomy Gate (N=725). Cells report standardised regression coefficients ( β\beta ) and p-values.
More in this topic

AI-Assisted Software Development

AI-assisted software development uses language models and coding agents to help people design, write, test, review, and maintain software.

See all 109 papers

Explore similar work

CardsList

  1. On the Prospects of Dynamic LLM Conversations in Software Development

    Aug 31, 2026Annemarie Wittig, Alina Mailach, Janet Siegmund +1LLM PromptingHuman-AI Interaction

    Leipzig, Leipzig University, Leipzig, 04109, Germany · Chemnitz University of Technology, Chemnitz, 09107, Germany · ScaDS.AI Dresden/Leipzig, Leipzig University, Leipzig, 04109, Germany

  2. LLMs Corrupt Your Documents When You Delegate

    Apr 17, 2026Philippe Laban, Tobias Schnabel, Jennifer NevilleLLM ReliabilityLong-Horizon LLM Agents

    Microsoft Research

  3. Anthropomorphism and Trust in Human-Large Language Model interactions

    Mar 1, 2026Akila Kadambi, Ylenia D'Elia, Tanishka Shah +8Anthropomorphism in AIHuman-AI Interaction

    Brain and Creativity Institute, Dornsife College of Letters, Arts and Sciences, University of Southern California, Los Angeles, CA, USA · USC Mrs. T.H. Chan Division of Occupational Science and Occupational Therapy, University of Southern California, Los Angeles, CA, USA · Psychiatry and Biobehavioral Sciences, David Geffen School of Medicine, University of California, Los Angeles, CA, USA +2