To LLM, or Not to LLM: How Designers and Developers Navigate LLMs as Tools or Teammates

• URL: http://arxiv.org/abs/2604.15344v1
• Date: Sun, 15 Mar 2026 06:58:08 GMT
• Title: To LLM, or Not to LLM: How Designers and Developers Navigate LLMs as Tools or Teammates
• Abstract summary: Large language models (LLMs) are increasingly integrated into design and development, yet decisions about their use are rarely binary or purely technical.<n>We report findings from a constructivist grounded theory study based on interviews with 33 designers and developers across three large technology organisations.
• Score: 11.663456969895462
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly integrated into design and development workflows, yet decisions about their use are rarely binary or purely technical. We report findings from a constructivist grounded theory study based on interviews with 33 designers and developers across three large technology organisations. Rather than evaluating LLMs solely by capability, participants reasoned about the role an LLM could occupy within a workflow and how that role would interact with existing structures of responsibility and organisational accountability. When LLMs were framed as tools under clear human control, their use was typically acceptable and could be integrated within existing governance structures. When framed as teammates with shared or ambiguous agency, practitioners expressed hesitation, particularly when responsibility for outcomes could not be clearly justified. At the same time, participants also described productive teammate configurations in which LLMs supported collaborative reasoning while remaining embedded within explicit oversight structures. We identify tool and teammate framings as recurring ways in which designers and developers position LLMs relative to human work and present an analytic rubric describing how role framing shapes decision authority, accountability ownership, oversight strategies, and organisational acceptability. By foregrounding design-time reasoning, this work reframes To LLM or Not to LLM as a sociotechnical positioning problem that emerges during system design rather than during post-deployment evaluation.

Related papers

• Characterizing Large Language Model Agentic Workflows: A Study on N8n Ecosystem [9.994953049271892]
  Large Language Models (LLMs) are rapidly being adopted in low-code and no-code automation platforms.<n>We present the first large-scale empirical study of LLM agentic in low-code automation platforms.
  arXiv  Detail & Related papers  (2026-06-27T23:57:01Z)
• Position: agentic AI orchestration should be Bayes-consistent [92.04373485710285]
  This paper argues that coherent decision-making requires Bayesian principles at the orchestration level of the agentic system.<n>It provides examples and design patterns to illustrate how beliefs and utility-aware policies can improve agentic AI orchestration.
  arXiv  Detail & Related papers  (2026-05-01T15:43:43Z)
• The Role of LLMs in Collaborative Software Design [9.27915132566963]
  Large Language Models (LLMs) shape collaborative group work in software engineering.<n>This study focuses on one such collaborative task, namely software design.
  arXiv  Detail & Related papers  (2026-04-10T09:00:33Z)
• Once Upon a Team: Investigating Bias in LLM-Driven Software Team Composition and Task Allocation [48.2168236140771]
  This study investigates whether LLMs exhibit bias in team composition and task assignment.<n>Using three LLMs and 3,000 simulated decisions, we find systematic disparities.<n>Our findings indicate that LLMs exacerbate demographic inequities in software engineering contexts.
  arXiv  Detail & Related papers  (2026-01-07T12:13:22Z)
• Walking the Tightrope of LLMs for Software Development: A Practitioners' Perspective [18.50207872331241]
  We investigated how Large Language Models impact software development and how to manage the impact from a developer's perspective.<n>We conducted 22 interviews with software practitioners across 3 rounds of data collection and analysis.<n>We identified the benefits (e.g., maintain software development flow, improve developers' mental model, and foster entrepreneurship) and disadvantages (e.g., negative impact on developers' personality and damage to developers' reputation) of using LLMs.
  arXiv  Detail & Related papers  (2025-11-09T15:49:55Z)
• LLM Agents Beyond Utility: An Open-Ended Perspective [50.809163251551894]
  We augment a pretrained LLM agent with the ability to generate its own tasks, accumulate knowledge, and interact extensively with its environment.<n>It can reliably follow complex multi-step instructions, store and reuse information across runs, and propose and solve its own tasks.<n>It remains sensitive to prompt design, prone to repetitive task generation, and unable to form self-representations.
  arXiv  Detail & Related papers  (2025-10-16T10:46:54Z)
• Language Agents Meet Causality -- Bridging LLMs and Causal World Models [50.79984529172807]
  We propose a framework that integrates causal representation learning with large language models. This framework learns a causal world model, with causal variables linked to natural language expressions. We evaluate the framework on causal inference and planning tasks across temporal scales and environmental complexities.
  arXiv  Detail & Related papers  (2024-10-25T18:36:37Z)
• Cognitive LLMs: Towards Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making [51.737762570776006]
  LLM-ACTR is a novel neuro-symbolic architecture that provides human-aligned and versatile decision-making. Our framework extracts and embeds knowledge of ACT-R's internal decision-making process as latent neural representations. Our experiments on novel Design for Manufacturing tasks show both improved task performance as well as improved grounded decision-making capability.
  arXiv  Detail & Related papers  (2024-08-17T11:49:53Z)
• Embodied LLM Agents Learn to Cooperate in Organized Teams [46.331162216503344]
  Large Language Models (LLMs) have emerged as integral tools for reasoning, planning, and decision-making. This paper introduces a framework that imposes prompt-based organization structures on LLM agents to mitigate these problems.
  arXiv  Detail & Related papers  (2024-03-19T06:39:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.