Human–AI Agent Collaboration for Industrial Problem Solving: A Case Study of operator tool concepts for problem solving during the delignification process in pulp production in the Pulp & Paper industry
Oct 2026· Adjunct Proceedings of the 14th Nordic Conference on Human-Computer Interaction· pp. 1-3· 0 citations· 5 references
TL;DR
Findings show the importance of explanations enabling users to verify agents reasoning, task delegation to preserve operator involvement, and adaptive HMI to support real-time collaboration in a high-stake industrial context.
Abstract
As automation levels increase, control room operators face increasingly complex roles. This paper presents an empirical evaluation of human-AI agent collaboration for problem solving during the delignification process in pulp production. Using a mid-fidelity prototype, evaluating with nine professional operators, we simulated agentic AI capabilities through wizard of Oz and assessed human AI agent interaction design. Structured around Cila's design framework, findings show the importance of explanations enabling users to verify agents reasoning, task delegation to preserve operator involvement, and adaptive HMI to support real-time collaboration. This study contributes empirically grounded design implications for human AI agent collaboration in a high-stake industrial context.
SDD reconstitutes, in specification-centric form, the contracts that vibe coding dissolves: accountability, verifiability, and transferability, and outlines a research agenda for future empirical validation.
J. Díaz, J. Gayoso, Andrea Cimminio et al.· 4 citations· ⚡1
Results from the proof‐of‐concept and proof‐of‐value evaluations provide initial evidence that the IATReBS method can help participants identify AI teammate requirements in complex problem‐solving contexts, particularly regarding feasibility, usability and perceived usefulness.
Wen-Qiang Li, J. Gou, L. Camarinha-Matos et al.· Systems research and behavio...· 0 citations
The emergence of AI agents is expected to reshape software engineering by moving beyond AI as assistants towards systems capable of planning, executing, and evaluating development tasks with increasing autonomy. This transition is particularly significant for embedded software organizations, where strict requirements f...
V. Kjellberg, Srijita Basu, Si-Min Sun et al.· 0 citations
This comprehensive review synthesises research on agentic and generative AI, human-AI cooperation, human-AI cooperation, algorithmic management, trust and explainability, decision-rights theory, and technology adoption into a conceptual multi-case framework comparing agentic AI adoption in sectors such as healthcare, f...
Dasaradha Arangi, Sreemanthula Jhansi, Minhaz Husain et al.· Journal of Progress in Artif...· 0 citations
An integrated delegation framework for preserving MHC in GPAI‐enabled human‐machine teams is presented and a nuanced autonomy‐control trade‐off is revealed: operators initially favored higher‐autonomy modes but reverted to more structured control when confronted with unexpected or non‐doctrinal agent behaviors.
K. van den Bosch, P. van Maanen, J. van Diggelen· The AI Magazine· 0 citations
This research introduces a tiered multi-agent architecture grounded in Human-Centered eXplainable AI principles that contributes an adaptable and generalizable framework and foundational artifacts for trustworthy AI teammates.
Jie Tao, Li-Na Zhou· Information Systems Frontier...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
