Guiding, Not Deciding: User Preferences in AI-Assisted Roles
Bibliographic record
Abstract
As artificial intelligence (AI) integrates into extended reality (XR), or known as XR×AI, a central design challenge emerges: how to balance AI assistance with user autonomy. This challenge presents a core dilemma: unassisted interfaces risk creating "hollow autonomy," where overwhelming choice undermines user confidence, while fully automated systems can impose a "tyranny of efficiency" that erodes agency. To investigate this tension, we conducted a study with 32 participants, comparing four distinct XR×AI strategies along a spectrum of intervention, from passive information display to direct recommendation, across two levels of task complexity. Our findings reveal a clear user preference for a collaborative middle ground that avoids the pitfalls of the extremes. While high intervention was decisively rejected for undermining agency, minimal support proved ineffective under complexity, leading to high cognitive load and low confidence. The most successful interfaces were those that acted as a "cognitive scaffold," collaborative partners that curated the decision space to reduce cognitive load and prevent errors, while leaving the final, empowering act of choice to the user. These results demonstrate that the goal of XR×AI design is not to create a system that thinks for us, but a partner that helps us think better.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.043 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".