MétaCan
Menu
Back to cohort

Situated Embodied XR Agents via Spatial Reasoning and Prompting

2025· article· W4416402445 on OpenAlexaff
Hyeonjin Kim, Eunseong Lee, Donghwan Shin, Kwang Lee, Taehei Kim, Hyeshim Kim, Jihoon An, Sung‐Hee Lee

Bibliographic record

Venuenot available
Typearticle
Language
FieldPsychology
TopicSocial Robot Interaction and HRI
Canadian institutionsKootenay Association for Science & Technology
Fundersnot available
KeywordsSituatedEmbodied cognitionContext (archaeology)Spatial contextual awarenessGestureState (computer science)Spatial intelligenceMotion (physics)

Abstract

fetched live from OpenAlex

As AI agents become increasingly integrated into daily life, new interaction paradigms are needed to support their presence as embodied, situated forms. We present a prototype that embeds LLM-powered agents within stylized virtual spaces anchored to a user’s real-world room in XR. The system provides spatial context to the LLM through structured scene descriptions, enabling agents to refer to and act upon their environment. A unified interaction loop integrates voice input, spatial reasoning, and motion planning with shared state across dialogue and gesture modules. This work demonstrates how spatially grounded agents can inhabit XR spaces for expressive, situated interaction.

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.003
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.008
Threshold uncertainty score0.027

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.001
Scholarly communication0.0020.002
Open science0.0010.003
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0080.001

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.

Opus teacher head0.031
GPT teacher head0.383
Teacher spread0.352 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations3
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicSocial Robot Interaction and HRIFrench-language works237,207