pith. sign in

arxiv: 2508.04108 · v4 · pith:5I5PRQNJnew · submitted 2025-08-06 · 💻 cs.HC

XARP Tools: An Extended Reality Platform for Humans and AI Agents

Arthur Caetano , Radha Kumaran , Kelvin Jou , Tobias H\"ollerer , Misha Sra This is my paper

Pith reviewed 2026-05-22 13:44 UTC · model grok-4.3

classification 💻 cs.HC
keywords XRPythonAI agentsWebSocketprototypingUnityspatial computinghuman-AI interaction
0
0 comments X

The pith

XARP enables Python-based XR development and AI agent participation by linking a Python server to Unity clients through WebSockets.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces XARP to address the divide between Python-centric AI work and C#/Unity-based XR development. By running application logic on a Python server that communicates with a Unity client using WebSocket messages, XARP supports live reloading of code and access from multiple platforms. It makes the toolkit available to humans as a library and to AI agents as callable tools via the Model Context Protocol. Evaluations involving 24 developers and a longitudinal study with two others showed expectations of better performance and confirmed faster iteration and simpler setup. The work highlights that this reduces engineering effort in spatial computing while noting challenges with asset-heavy or high-performance projects.

Core claim

XARP is a toolkit for XR-AI prototyping where logic runs in Python and controls Unity via WebSocket messages. This architecture provides compatibility across clients, live code reloading without redeployment, and direct integration for AI agents. User testing and benchmarks validate improved development speed, with tracking data close to 72 FPS and AI agents using 19 percent fewer tokens than equivalent C# code.

What carries the argument

The Python server to Unity client WebSocket messaging system that executes XR logic and permits dynamic reloading.

If this is right

  • Human developers can build and test XR applications more quickly using familiar Python tools.
  • AI agents gain the ability to directly develop or modify XR applications through tool calls.
  • Research in human-AI interaction in spatial environments becomes accessible without deep game engine expertise.
  • Prototyping cycles shorten because changes in Python do not require rebuilding the client side.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Adoption could lead to new research directions where AI agents iteratively design XR experiences in collaboration with humans.
  • Similar architectures might apply to other domains where Python AI meets real-time simulation engines.
  • Future versions could address the identified limitations by optimizing for asset management and performance.

Load-bearing premise

The messaging and reloading mechanism will provide adequate responsiveness for the bulk of XR-AI prototype work.

What would settle it

Observe whether an XR prototype involving detailed 3D models and complex interactions experiences noticeable delays or reduced frame rates when implemented with XARP versus standard methods.

Figures

Figures reproduced from arXiv: 2508.04108 by Arthur Caetano, Kelvin Jou, Misha Sra, Radha Kumaran, Tobias H\"ollerer.

Figure 1
Figure 1. Figure 1: Toolkit Architecture: XARP provides a unified abstraction for XR, accessible to both humans and AI agents. The [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Three in-house case studies used to surface require [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Video Walkthrough Study Measurements: Perfor￾mance Expectancy drove Behavioral Intention [48], while XARP’s Effort Expectancy was better rated than its Facili￾tating Conditions. A customized survey based on common toolkit goals [28] showed participants valued XARP for re￾ducing authoring time, empowering new audiences, and replicating solutions, but less for providing paths of least resistance. Following t… view at source ↗
Figure 4
Figure 4. Figure 4: Likert-scale responses to the four UTAUT constructs and the six HCITG constructs, aggregated across our subject [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: UTAUT Score: The construct Facilitating Condi￾tions was rated significantly lower than Effort Expectancy by participants [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: HCITG Scores: The construct Creating Paths of Least Resistance was rated significantly lower than Reducing Authoring Time and Complexity, Empowering New Audiences, and Enabling Replication of Existing Solutions High-level abstraction. Participants valued the simplicity and clarity of XARP’s functions and its ability to hide unnecessary tech￾nical detail. P3 emphasized “the efficiency, organization/simplici… view at source ↗
read the original abstract

Building XR-AI research prototypes requires navigating two largely separate ecosystems. Mainstream XR development relies on C#/C++ and game engines, while AI development is centered on Python. This toolchain fragmentation slows down contributions to human-AI spatial interaction research. To broaden access to XR development in the Python ecosystem, we present XARP (XR Agent-ready Remote Procedures), a toolkit for rapid XR-AI prototyping in Python. XARP application logic runs on a Python server and controls a Unity client through WebSocket messages. This architecture enables compatibility with multiple client platforms and live reloading of application code without client redeployment. XARP is available to humans as a library and to AI agents as callable tools and through Model Context Protocol. We designed XARP through formative case studies and refined it through an early acceptance evaluation with 24 XR and AI developers and a six-week longitudinal study with two developers building an independent research project. Potential users expected the toolkit to improve their performance and facilitate development. Sustained use confirmed faster iteration and easier setup compared to conventional XR workflows, with asset-intensive and performance-critical projects emerging as the clearest limitations. Technical benchmarks show that hand and head tracking data streaming was close to the device refresh rate of 72 FPS, and that AI agents using XARP consumed 19% fewer tokens than those writing equivalent C# Unity code. Beyond broadening access to XR development, XARP reduces engineering friction in spatial computing research and opens new pathways for AI agents to participate in XR application development. XARP is open source and available at https://github.com/hal-ucsb/xarp.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 3 minor

Summary. The manuscript introduces XARP (XR Agent-ready Remote Procedures), a toolkit for rapid XR-AI prototyping that runs application logic on a Python server and controls a Unity client via WebSocket messages. This enables live code reloading without client redeployment, compatibility across platforms, and integration for both human developers (as a library) and AI agents (as callable tools and via Model Context Protocol). The work is motivated by toolchain fragmentation between Python-centric AI research and C#/C++-based XR development. Evidence includes formative case studies, an acceptance evaluation with 24 XR and AI developers, a six-week longitudinal deployment with two developers, and technical benchmarks showing tracking data streaming near 72 FPS along with 19% fewer tokens consumed by AI agents using XARP versus equivalent C# Unity code. The central claim is that XARP broadens access to XR development, reduces engineering friction in spatial computing research, and opens pathways for AI agents to participate in XR application development.

Significance. If the claims hold, the work addresses a genuine practical barrier in human-AI spatial interaction research by providing an open-source bridge between Python AI ecosystems and XR platforms. The direct evidence from the 24-developer acceptance study, the longitudinal deployment, and the reported performance metrics (72 FPS tracking and token reduction) strengthens the usability arguments. Open-source release at the provided GitHub repository is a clear strength that supports reproducibility and further adoption.

major comments (1)
  1. [Technical benchmarks] Technical benchmarks section: while hand and head tracking data streaming is reported as close to the device refresh rate of 72 FPS, no round-trip latency measurements are provided for bidirectional control messages, Python-initiated object manipulation, or state queries. This quantification is necessary to support the assumption that the WebSocket architecture remains responsive enough for the majority of XR-AI prototypes (as stated in the abstract and the discussion of limitations for only asset-intensive cases).
minor comments (3)
  1. [User studies] The acceptance study (24 developers) and longitudinal study (two developers) are described as self-selected; a brief discussion of potential selection bias or how participants were recruited would improve the strength of the usability claims without altering the core contribution.
  2. [Abstract] Abstract: the phrase 'Potential users expected the toolkit to improve their performance' is ambiguous—clarify whether this refers to development iteration speed or runtime performance.
  3. [Overall] Ensure consistent use of terminology (e.g., 'XARP remote-procedure architecture' vs. 'WebSocket messaging') across sections to avoid minor confusion for readers unfamiliar with the system.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the positive evaluation of XARP's significance, the recognition of our user studies and open-source release, and the constructive technical feedback. We address the major comment below and will revise the manuscript to incorporate the suggested measurements.

read point-by-point responses

  1. Referee: Technical benchmarks section: while hand and head tracking data streaming is reported as close to the device refresh rate of 72 FPS, no round-trip latency measurements are provided for bidirectional control messages, Python-initiated object manipulation, or state queries. This quantification is necessary to support the assumption that the WebSocket architecture remains responsive enough for the majority of XR-AI prototypes (as stated in the abstract and the discussion of limitations for only asset-intensive cases).

    Authors: We agree that round-trip latency data would strengthen the evaluation of responsiveness for bidirectional control flows. Our existing benchmarks prioritize high-frequency tracking streaming (near 72 FPS) because it is the most latency-sensitive aspect of XR experiences. To address this gap, the revised manuscript will include new measurements of round-trip times for Python-initiated commands, object manipulations, and state queries under representative XR-AI prototype workloads. These additions will directly support the claim that the architecture remains suitable for the majority of use cases, while preserving the existing discussion of limitations for asset-intensive applications. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The paper's central claims about reducing engineering friction and enabling AI agent participation in XR development are supported by independent empirical evidence: formative case studies, an acceptance evaluation with 24 XR/AI developers, a six-week longitudinal study with two developers, and technical benchmarks (hand/head tracking near 72 FPS, 19% fewer tokens for AI agents). No mathematical derivations, fitted parameters renamed as predictions, or load-bearing self-citations appear in the provided text; the WebSocket/Python architecture is presented as an explicit design choice rather than derived from prior self-referential results. The derivation chain remains self-contained against external benchmarks and user studies.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The contribution is an engineering artifact whose central claims rest on standard networking assumptions and the practical utility of the chosen split between Python logic and Unity rendering.

axioms (1)
  • domain assumption WebSocket provides sufficiently low-latency bidirectional communication for head and hand tracking at headset refresh rates
    Invoked to support the claim that streaming stays close to 72 FPS.
invented entities (1)
  • XARP remote-procedure architecture no independent evidence
    purpose: Bridge Python AI code with Unity XR clients while supporting live reloading and agent tool calling
    The toolkit itself is the primary new artifact; no independent physical evidence is offered beyond the software release.

pith-pipeline@v0.9.0 · 5828 in / 1311 out tokens · 49939 ms · 2026-05-22T13:44:51.993243+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

60 extracted references · 60 canonical work pages · 1 internal anchor

  1. [1]

    Setareh Aghel Manesh, Tianyi Zhang, Yuki Onishi, Kotaro Hara, Scott Bateman, Jiannan Li, and Anthony Tang. 2024. How people prompt generative ai to create interactive vr scenes. InProceedings of the 2024 ACM Designing Interactive Systems Conference. 2319–2340

    work page 2024

  2. [2]

    2024.Introducing the Model Context Protocol

    Anthropic. 2024.Introducing the Model Context Protocol. https://www.anthropic. com/news/model-context-protocol

    work page 2024

  3. [3]

    Dan Bohus, Sean Andrist, Nick Saw, Ann Paradiso, Ishani Chakraborty, and Mahdi Rad. 2024. Sigma: An open-source interactive system for mixed-reality task assistance research–extended abstract. In2024 IEEE conference on virtual reality and 3D user interfaces abstracts and workshops (VRW). IEEE, 889–890

    work page 2024

  4. [4]

    Borchers

    Jan O. Borchers. 2000. A pattern approach to interaction design. InProceed- ings of the 3rd Conference on Designing Interactive Systems: Processes, Prac- tices, Methods, and Techniques(New York City, New York, USA)(DIS ’00). As- sociation for Computing Machinery, New York, NY, USA, 369–378. https: //doi.org/10.1145/347642.347795

    work page doi:10.1145/347642.347795 2000

  5. [5]

    Ingo Börsting, Markus Heikamp, Marc Hesenius, Wilhelm Koop, and Volker Gruhn. 2022. Software Engineering for Augmented Reality - A Research Agenda. Proc. ACM Hum.-Comput. Interact.6, EICS, Article 155 (June 2022), 34 pages. https://doi.org/10.1145/3532205

    work page doi:10.1145/3532205 2022

  6. [6]

    Dibyendu Brinto Bose and Chris Brown. 2024. An Empirical Study on Current Practices and Challenges of Core AR/VR Developers. InProceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering Workshops (Sacramento, CA, USA)(ASEW ’24). Association for Computing Machinery, New York, NY, USA, 233–238. https://doi.org/10.1145/369162...

    work page doi:10.1145/3691621.3694956 2024

  7. [7]

    Riccardo Bovo, Steven Abreu, Karan Ahuja, Eric J Gonzalez, Li-Te Cheng, and Mar Gonzalez-Franco. 2025. Embardiment: an embodied ai agent for productivity in xr. In2025 IEEE Conference Virtual Reality and 3D User Interfaces (VR). IEEE, 708–717

    work page 2025

  8. [8]

    Kadir Burak Buldu, Süleyman Özdel, Ka Hei Carrie Lau, Mengdi Wang, Daniel Saad, Sofie Schönborn, Auxane Boch, Enkelejda Kasneci, and Efe Bozkir. 2025. Cuify the xr: An open-source package to embed llm-powered conversational agents in xr. In2025 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR). IEEE, 192–197

    work page 2025

  9. [9]

    Margaret Burnett, Curtis Cook, and Gregg Rothermel. 2004. End-user software engineering.Commun. ACM47, 9 (2004), 53–58

    work page 2004

  10. [10]

    Arthur Caetano, Alejandro Aponte, and Misha Sra. 2025. A design toolkit for task support with mixed reality and artificial intelligence.Frontiers in Virtual Reality6 (2025), 1536393

    work page 2025

  11. [11]

    Runze Cai, Nuwan Janaka, Hyeongcheol Kim, Yang Chen, Shengdong Zhao, Yun Huang, and David Hsu. 2025. AiGet: Transforming Everyday Moments into Hidden Knowledge Discovery with AI Assistance on Smart Glasses. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 1–26

    work page 2025

  12. [12]

    Sonia Castelo, Joao Rulff, Erin McGowan, Bea Steers, Guande Wu, Shaoyu Chen, Iran Roman, Roque Lopez, Ethan Brewer, Chen Zhao, et al. 2023. Argus: Visual- ization of ai-assisted task guidance in ar.IEEE Transactions on Visualization and Computer Graphics30, 1 (2023), 1313–1323

    work page 2023

  13. [13]

    Melvin E Conway. 1968. How do committees invent.Datamation14, 4 (1968), 28–31

    work page 1968

  14. [14]

    Fernanda De La Torre, Cathy Mengying Fang, Han Huang, Andrzej Banburski- Fahey, Judith Amores Fernandez, and Jaron Lanier. 2024. LLMR: Real-time Prompting of Interactive Worlds using Large Language Models. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). Association for Computing Machinery, New Yo...

    work page doi:10.1145/3613904.3642579 2024

  15. [15]

    Fernanda De La Torre, Cathy Mengying Fang, Han Huang, Andrzej Banburski- Fahey, Judith Amores Fernandez, and Jaron Lanier. 2024. Llmr: Real-time prompt- ing of interactive worlds using large language models. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–22

    work page 2024

  16. [16]

    Mustafa Doga Dogan, Eric J Gonzalez, Karan Ahuja, Ruofei Du, Andrea Colaço, Johnny Lee, Mar Gonzalez-Franco, and David Kim. 2024. Augmented Object Intelligence with XR-Objects. InProceedings of the 37th Annual ACM Symposium on User Interface Software and Technology(Pittsburgh, PA, USA)(UIST ’24). As- sociation for Computing Machinery, New York, NY, USA, A...

    work page doi:10.1145/3654777.3676379 2024

  17. [17]

    João Marcelo Evangelista Belo, Anna Maria Feit, Tiare Feuchtner, and Kaj Grøn- bæk. 2021. XRgonomics: Facilitating the Creation of Ergonomic 3D Interfaces. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems (Yokohama, Japan)(CHI ’21). Association for Computing Machinery, New York, NY, USA, Article 290, 11 pages. https://doi.or...

    work page doi:10.1145/3411764.3445349 2021

  18. [18]

    João Marcelo Evangelista Belo, Mathias N Lystbæk, Anna Maria Feit, Ken Pfeuffer, Peter Kán, Antti Oulasvirta, and Kaj Grønbæk. 2022. Auit–the adaptive user interfaces toolkit for designing xr applications. InProceedings of the 35th Annual ACM Symposium on User Interface Software and Technology. 1–16

    work page 2022

  19. [19]

    Nicola K Gale, Gemma Heath, Elaine Cameron, Sabina Rashid, and Sabi Redwood

    work page

  20. [20]

    Using the framework method for the analysis of qualitative data in multi- disciplinary health research.BMC medical research methodology13, 1 (2013), 117

    work page 2013

  21. [21]

    Daniele Giunchi, Nels Numan, Elia Gatti, and Anthony Steed. 2024. Dream- CodeVR: Towards Democratizing Behavior Design in Virtual Reality with Speech- Driven Programming. In2024 IEEE Conference Virtual Reality and 3D User Inter- faces (VR). 579–589. https://doi.org/10.1109/VR58804.2024.00078

    work page doi:10.1109/vr58804.2024.00078 2024

  22. [22]

    Saul Greenberg and Bill Buxton. 2008. Usability evaluation considered harmful (some of the time). InProceedings of the SIGCHI Conference on Human Factors in Computing Systems(Florence, Italy)(CHI ’08). Association for Computing Ma- chinery, New York, NY, USA, 111–120. https://doi.org/10.1145/1357054.1357074

    work page doi:10.1145/1357054.1357074 2008

  23. [23]

    Amal Hashky, Benjamin Rheault, Ahmed Rageeb Ahsan, Brett Benda, Tyler Au- dino, Samuel Lonneman, and Eric D Ragan. 2024. Multi-Modal User Modeling for Task Guidance: A Dataset for Real-Time Assistance with Stress and Interruption Dynamics. In2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW). IEEE, 544–550

    work page 2024

  24. [24]

    Xiyun Hu, Dizhi Ma, Fengming He, Zhengzhe Zhu, Shao-Kang Hsia, Chenfei Zhu, Ziyi Liu, and Karthik Ramani. 2025. GesPrompt: Leveraging Co-Speech Gestures to Augment LLM-Based Interaction in Virtual Reality. InProceedings of the 2025 ACM Designing Interactive Systems Conference. 59–80

    work page 2025

  25. [25]

    Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R Narasimhan. 2024. SWE-bench: Can Language Models Resolve Real-world Github Issues?. InThe Twelfth International Conference on Learning Representations. https://openreview.net/forum?id=VTF8yNQM66

    work page 2024

  26. [26]

    Frederick Phillips Brooks Jr. 1987. No Silver Bullet Essence and Accidents of Software Engineering.Computer20, 4 (1987), 10–19. https://doi.org/10.1109/ MC.1987.1663532

    work page arXiv 1987

  27. [27]

    Heewoo Jun and Alex Nichol. 2023. Shap-e: Generating conditional 3d implicit functions.arXiv preprint arXiv:2305.02463(2023)

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  28. [28]

    Alan C Kay. 1977. Microelectronics and the personal computer.Scientific Ameri- can237, 3 (1977), 230–245. Caetano et al

    work page 1977

  29. [29]

    David Ledo, Steven Houben, Jo Vermeulen, Nicolai Marquardt, Lora Oehlberg, and Saul Greenberg. 2018. Evaluation Strategies for HCI Toolkit Research. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (Montreal QC, Canada)(CHI ’18). Association for Computing Machinery, New York, NY, USA, 1–17. https://doi.org/10.1145/3173574.3173610

    work page doi:10.1145/3173574.3173610 2018

  30. [30]

    Jaewook Lee, Andrew D Tjahjadi, Jiho Kim, Junpu Yu, Minji Park, Jiawen Zhang, Jon E Froehlich, Yapeng Tian, and Yuhang Zhao. 2024. CookAR: Affordance augmentations in wearable AR to support kitchen tool interactions for people with low vision. InProceedings of the 37th Annual ACM Symposium on User Interface Software and Technology. 1–16

    work page 2024

  31. [31]

    Jaewook Lee, Jun Wang, Elizabeth Brown, Liam Chu, Sebastian S Rodriguez, and Jon E Froehlich. 2024. GazePointAR: A context-aware multimodal voice assistant for pronoun disambiguation in wearable augmented reality. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–20

    work page 2024

  32. [32]

    Chenyi Li, Guande Wu, Gromit Yeuk-Yin Chan, Dishita Gdi Turakhia, Sonia Castelo Quispe, Dong Li, Leslie Welch, Claudio Silva, and Jing Qian. 2025. Satori: Towards Proactive AR Assistant with Belief-Desire-Intention User Modeling. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Machinery,...

    work page doi:10.1145/3706598.3714188 2025

  33. [33]

    Jiefeng Li, Siyuan Bian, Chao Xu, Zhicun Chen, Lixin Yang, and Cewu Lu. 2025. HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-Body Mesh Recovery.IEEE Transactions on Pattern Analysis and Machine Intelligence47, 4 (2025), 2754–2769. https://doi.org/10.1109/TPAMI.2025.3528979

    work page doi:10.1109/tpami.2025.3528979 2025

  34. [34]

    Zhipeng Li, Christoph Gebhardt, Yves Inglin, Nicolas Steck, Paul Streli, and Christian Holz. 2024. SituationAdapt: Contextual UI Optimization in Mixed Reality with Situation Awareness via LLM Reasoning. InProceedings of the 37th Annual ACM Symposium on User Interface Software and Technology(Pittsburgh, PA, USA)(UIST ’24). Association for Computing Machine...

    work page doi:10.1145/3654777.3676470 2024

  35. [35]

    Chen-Chieh Liao, Zhihao Yu, and Hideki Koike. 2025. ShiftingGolf: Gross Motor Skill Correction Using Redirection in VR.IEEE Transactions on Visualization and Computer Graphics31, 5 (2025), 3429–3439. https://doi.org/10.1109/TVCG.2025. 3549170

    work page doi:10.1109/tvcg.2025 2025

  36. [36]

    Spencer Lin, Basem Rizk, Miru Jun, Andy Artze, Caitlín Sullivan, Sharon Mozgai, and Scott Fisher. 2024. Estuary: A Framework For Building Multimodal Low- Latency Real-Time Socially Interactive Agents. InProceedings of the 24th ACM International Conference on Intelligent Virtual Agents. 1–3

    work page 2024

  37. [37]

    Sara Mandic, Rhys Tracy, and Misha Sra. 2023. ARFit: Pose-based Exercise Feedback with Mobile AR. InProceedings of the 2023 ACM Symposium on Spatial User Interaction(Sydney, NSW, Australia)(SUI ’23). Association for Computing Machinery, New York, NY, USA, Article 45, 3 pages. https://doi.org/10.1145/ 3607822.3618008

    work page arXiv 2023

  38. [38]

    Ben Moseley and Peter Marks. 2006. Out of the tar pit.Software Practice Ad- vancement (SPA)2006 (2006)

    work page 2006

  39. [39]

    Hudson, and Randy Pausch

    Brad Myers, Scott E. Hudson, and Randy Pausch. 2000. Past, present, and future of user interface software tools.ACM Trans. Comput.-Hum. Interact.7, 1 (March 2000), 3–28. https://doi.org/10.1145/344949.344959

    work page doi:10.1145/344949.344959 2000

  40. [40]

    1993.A small matter of programming: perspectives on end user computing

    Bonnie A Nardi. 1993.A small matter of programming: perspectives on end user computing. MIT press

    work page 1993

  41. [41]

    Nathalia Nascimento, Everton Guimaraes, Sai Sanjna Chintakunta, and San- thosh Anitha Boominathan. 2025. How Effective are LLMs for Data Science Coding? A Controlled Experiment. In2025 IEEE/ACM 22nd International Confer- ence on Mining Software Repositories (MSR). 211–222. https://doi.org/10.1109/ MSR66628.2025.00041

    work page arXiv 2025

  42. [42]

    Nels Numan, Gabriel Brostow, Suhyun Park, Simon Julier, Anthony Steed, and Jessica Van Brummelen. 2025. CoCreatAR: Enhancing authoring of outdoor augmented reality experiences through asymmetric collaboration. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 1–22

    work page 2025

  43. [43]

    Raf Ramakers, Fraser Anderson, Tovi Grossman, and George Fitzmaurice. 2016. RetroFab: A Design Tool for Retrofitting Physical Interfaces using Actuators, Sensors and 3D Printing. InProceedings of the 2016 CHI Conference on Human Factors in Computing Systems(San Jose, California, USA)(CHI ’16). Association for Computing Machinery, New York, NY, USA, 409–41...

    work page arXiv 2016

  44. [44]

    Symeon Retalis, Petros Georgiakakis, and Yannis Dimitriadis. 2006. Elic- iting design patterns for e-learning systems.Computer Science Educa- tion16, 2 (2006), 105–118. https://doi.org/10.1080/08993400600773323 arXiv:https://doi.org/10.1080/08993400600773323

    work page doi:10.1080/08993400600773323 2006

  45. [45]

    Benjamin Rheault, Shivvrat Arya, Akshay Vyas, Jikai Wang, Rohith Peddi, Brett Bendall, Vibhav Gogate, Nicholas Ruozzi, Yu Xiang, and Eric D Ragan. 2024. Predictive task guidance with artificial intelligence in augmented reality. In2024 IEEE conference on virtual reality and 3D user interfaces abstracts and workshops (VRW). IEEE, 973–974

    work page 2024

  46. [46]

    Shital Shah, Debadeepta Dey, Chris Lovett, and Ashish Kapoor. 2018. AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles. InField and Service Robotics, Marco Hutter and Roland Siegwart (Eds.). Springer Interna- tional Publishing, Cham, 621–635

    work page 2018

  47. [47]

    2004.The Law of Leaky Abstractions

    Joel Spolsky. 2004.The Law of Leaky Abstractions. Apress, Berkeley, CA, 197–202. https://doi.org/10.1007/978-1-4302-0753-5_26

    work page doi:10.1007/978-1-4302-0753-5_26 2004

  48. [48]

    Sruti Srinidhi, Edward Lu, and Anthony Rowe. 2024. XaiR: An XR Platform that Integrates Large Language Models with the Physical World. In2024 IEEE International Symposium on Mixed and Augmented Reality (ISMAR). 759–767. https://doi.org/10.1109/ISMAR62088.2024.00091

    work page doi:10.1109/ismar62088.2024.00091 2024

  49. [49]

    Morris, Gordon B

    Viswanath Venkatesh, Michael G. Morris, Gordon B. Davis, and Fred D. Davis

    work page

  50. [50]

    User acceptance of information technology: Toward a unified view,

    User Acceptance of Information Technology: Toward a Unified View.MIS Quarterly27, 3 (2003), 425–478. http://www.jstor.org/stable/30036540

    work page arXiv 2003

  51. [51]

    Michel Wermelinger. 2023. Using GitHub Copilot to Solve Simple Programming Problems. InProceedings of the 54th ACM Technical Symposium on Computer Science Education V. 1(Toronto ON, Canada)(SIGCSE 2023). Association for Computing Machinery, New York, NY, USA, 172–178. https://doi.org/10.1145/ 3545945.3569830

    work page arXiv 2023

  52. [52]

    Niall Winters and Yishay Mor. 2009. Dealing with abstraction: Case study gener- alisation as a method for eliciting design patterns.Computers in Human Behavior 25, 5 (2009), 1079–1088. https://doi.org/10.1016/j.chb.2009.01.007 Including the Special Issue: Design Patterns for Augmenting E-Learning Experiences

    work page doi:10.1016/j.chb.2009.01.007 2009

  53. [53]

    Guande Wu, Jing Qian, Sonia Castelo Quispe, Shaoyu Chen, João Rulff, and Claudio Silva. 2024. Artist: Automated text simplification for task guidance in augmented reality. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–24

    work page 2024

  54. [54]

    Jianfeng Xiang, Zelong Lv, Sicheng Xu, Yu Deng, Ruicheng Wang, Bowen Zhang, Dong Chen, Xin Tong, and Jiaolong Yang. 2025. Struc- tured 3D Latents for Scalable and Versatile 3D Generation. InCVPR

    work page 2025

  55. [55]

    https://www.microsoft.com/en-us/research/publication/structured-3d- latents-for-scalable-and-versatile-3d-generation/

    work page

  56. [56]

    Chengyuan Xu, Radha Kumaran, Noah Stier, Kangyou Yu, and Tobias Höllerer

    work page

  57. [57]

    In2024 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)

    Multimodal 3D Fusion and In-Situ Learning for Spatially Aware AI. In2024 IEEE International Symposium on Mixed and Augmented Reality (ISMAR). IEEE, 485–494

    work page

  58. [58]

    Xuhai Xu, Anna Yu, Tanya R. Jonker, Kashyap Todi, Feiyu Lu, Xun Qian, João Marcelo Evangelista Belo, Tianyi Wang, Michelle Li, Aran Mun, Te-Yen Wu, Junxiao Shen, Ting Zhang, Narine Kokhlikyan, Fulton Wang, Paul Soren- son, Sophie Kim, and Hrvoje Benko. 2023. XAIR: A Framework of Explain- able AI in Augmented Reality. InProceedings of the 2023 CHI Conferen...

    work page doi:10.1145/3544548.3581500 2023

  59. [59]

    Nur Yildirim, Changhoon Oh, Deniz Sayar, Kayla Brand, Supritha Challa, Violet Turri, Nina Crosby Walton, Anna Elise Wong, Jodi Forlizzi, James McCann, and John Zimmerman. 2023. Creating Design Resources to Scaffold the Ideation of AI Concepts. InProceedings of the 2023 ACM Designing Interactive Systems Conference(Pittsburgh, PA, USA)(DIS ’23). Association...

    work page doi:10.1145/3563657.3596058 2023

  60. [60]

    Dong Woo Yoo, Hamid Tarashiyoun, and Mohsen Moghaddam. 2023. Modeling gaze behavior for real-time estimation of visual attention and expertise level in augmented reality. In2023 IEEE international symposium on mixed and augmented reality adjunct (ISMAR-Adjunct). IEEE, 487–492

    work page 2023