Letting the AI decide what the AI should code? On responsibility and accountability in requirements-driven software evolution
Loading...
Authors
Author (Corporation)
Publication date
2026
Type of student thesis
Course of study
Collections
Type
04B - Conference paper
Editors
Editor (Corporation)
Supervisor
Parent work
Proceedings 2026 IEEE 34th International Requirements Engineering Conference (RE)
Special issue
DOI of the original publication
Link
Related research data
Series
Series number
Volume
Issue / Number
Pages / Duration
486-493
Patent number
Publisher / Publishing institution
IEEE
Place of publication / Event location
Montreal
Edition
Version
Programming language
Assignee
Practice partner / Client
Abstract
AI agents can now take software change requests from a natural-language description to code changes. Capability alone, however, does not answer whether an agent should be allowed to act. We frame that upstream decision as a requirements engineering problem: before implementation starts, a team must decide whether a request may be delegated to AI, handled collaboratively, or kept under human control, all while humans remain accountable for the outcome. Existing work mainly automates implementation or isolated RE tasks, but offers little guidance for assigning responsibility. We therefore propose RADAR (Responsibility-Aware Delegation with Auditable Reasoning), a framework that treats responsibility allocation as a requirements artifact. The framework evaluates each incoming request along observable dimensions: clarity, traceability, scope, risk (including domain criticality), and compliance. It then routes the request through four stages: input reception, information assessment, compliance checking, and responsibility assignment. The result is one of four responsibility levels, ranging from autonomous AI execution to human-only handling. Every decision produces an explainable, auditable package with evidence, rationale, uncertainty notes, and required approvals. We present the framework, describe an initial prototype, report preliminary findings from expert interviews (N=4), and outline a twopart evaluation that studies whether the allocation criteria are defensible and whether the outputs support validation, override, and audit.
Keywords
Subject (DDC)
Event
2026 IEEE 34th International Requirements Engineering Conference (RE)
Exhibition start date
Exhibition end date
Conference start date
17.08.2026
Conference end date
21.08.2026
Date of the last check
ISBN
979-8-3315-4851-3
979-8-3315-4852-0
979-8-3315-4852-0
ISSN
Language
English
Created during FHNW affiliation
Yes
Strategic action fields FHNW
Publication status
Published
Review
peer-reviewed
Open access category
Closed
Citation
Lüthy, R., & Seyff, N. (2026). Letting the AI decide what the AI should code? On responsibility and accountability in requirements-driven software evolution. Proceedings 2026 IEEE 34th International Requirements Engineering Conference (RE), 486–493. https://doi.org/10.1109/re68928.2026.00050