Feedforward shows a user what an action will do before they commit to it. In VR these previews are usually hand-coded and tightly coupled to one application, which makes them hard to reuse and the design space hard to explore. BeatriXR organises feedforward into reusable blocks — how a preview is triggered, what it shows, and how it ends — authored from a settings panel rather than in code. A language-model advisor can suggest configurations as a mixed-initiative aid, leaving the final choice to the designer.
Designers must coordinate many interdependent choices — when a preview triggers, how the action and outcome are shown, how it transitions back — usually coded ad hoc inside a game engine. Even with a toolkit, the space of combinations is large enough that good configurations are easy to miss.
Direct feedforward = showing the user, with contextual previews, exactly what an interaction will do. BeatriXR focuses on the visual side of that, deeply.
Create, visualise and customise direct feedforward with avatars and interface panels, mapped onto an established design space and the triggering / previewing / exiting phases.
A generative model proposes configuration alternatives to help designers explore the space — a mixed-initiative aid, not an autopilot.
Built in Unity with MRTK 3, demonstrated in an immersive hazardous-materials training scenario; code is open on GitHub.
XR experts assessed the toolkit, its configuration interface, and how useful LLM-generated suggestions were for feedforward design.
A browser recreation of what BeatriXR’s in-headset settings panel controls. Adjust how a preview demonstrates the action “operate the control” — the avatar, viewpoint, rendering, trigger and exit — and see the configuration described below. Switching to AI advisor loads a configuration in line with what experts in the study favoured.
Illustrative recreation — a stylized scene and avatar, not the paper’s real VR renders or LLM. It mirrors BeatriXR’s actual settings (avatar type, view, ghosting, duplication, dislocation, signifiers, trigger and exit). The AI preset reflects what experts in the study tended to prefer; see the PDF for the real system.
BeatriXR operationalises an existing feedforward design space (Muresan et al.) into three reusable phases. A designer sets each one from a panel; because the settings combine, the space of possible previews is large — which is what the reusable blocks and the LLM advisor are there to help manage.
What makes a preview start playing.
How the action is demonstrated.
When and how the preview goes away.
The dimensions and option values above are taken from the paper’s design space; it builds on Muresan et al.’s feedforward taxonomy. See the PDF for the full treatment.
At runtime BeatriXR is three elements working together — a guidance UI, avatar demonstrations, and an optional AI module.
The Task Panel shows progress and alternative interactions as a stack of cards. The Settings Panel exposes the Trigger / Preview / Exit options as arrow-cyclers and toggles, with an explanation of each.
A disembodied avatar acts out the interaction using inverse kinematics, with no prior scene knowledge. A compare mode shows two interaction options side by side in separate panels.
A local language model reads the current settings and task sequence and proposes alternative configurations. The expert can adopt the overrides or keep customising — control stays human.
An exploratory, expert-driven evaluation — first formative, then a fuller session on the final UI and the LLM suggestions.
A formative mockup study, then an exploratory study of the finished interface and four LLM advisors.
Their feedforward configurations aligned well with reference rankings (means ~12–13 / 15). Feedback turned radio buttons into toggles.
Touch a virtual mouse, laser-grab a beaker, and grab to turn a sink — chosen to span common VR interaction styles.
GPT-OSS-120B, Mistral Small 3.2, DeepSeek R1 and GPT-5 Mini, scored on quality, usefulness and resulting feedforward.
Results are exploratory and qualitative — expert perceptions, not task-performance measures — but consistently positive about the panel’s structure.
Across the three tasks (76 / 91 / 88% by task), experts read the settings panel correctly on first exposure — understanding rose as they got used to it.
Most with professional or academic XR experience. Self-rated comprehensibility climbed from 5.8 to about 6.4 out of 7 over the tasks.
Every model produced reasonable suggestions; alignment with expert reasoning was only partial. DeepSeek R1 stood out for clear, context-aware output.
Experts liked clustering settings into Trigger / Preview / Exit, but flagged icon ambiguity and information density. They preferred partial, ghosted avatars and manual triggers, and rejected previews that take control away from the user.
Seven modules connected by APIs, so any piece can be swapped as long as it honours the contract.
The Mixed Reality Toolkit handles complex VR interactions with minimal setup — mostly assigning components to scene elements.
A Rocketbox model with per-interaction animations, adapted on the fly by inverse kinematics and rendered opaque or transparent, full or partial.
Served via LM Studio with temperature 0, top-k 1, top-p 0 so identical inputs give identical suggestions.
The evaluation is expert feedback only. It cannot yet quantify effects on development speed, usability, or how well end users actually learn.
No systematic comparison against rule-based alternatives, and runtime adaptation is not yet validated — treat the advisor as an ideation aid.
Audio and haptic modifiers were deliberately left out to go deep on visual cues, so multimodal coverage is incomplete.
The breadth of options can overwhelm. Presets, templates and adaptive interfaces are likely needed for broader audiences.
BeatriXR operationalises a feedforward design space into reusable Trigger / Preview / Exit blocks, lets domain experts author VR guidance from a panel instead of code, and adds an LLM advisor to widen the options they consider — while leaving the final call to them. Early expert feedback is encouraging on both the interface and the AI assistance, especially for novices.