pith. sign in

arxiv: 2605.28154 · v1 · pith:I4IA74O3new · submitted 2026-05-27 · 💻 cs.HC · cs.RO

Robo-Blocks: Generative Scaffolding in End-User Design and Programming of Social Robots

Arissa J. Sato , Callie Y. Kim , Nathan Thomas White , Abhinav Maneesh , Yuqing Wang , Hui-Ru Ho , Bilge Mutlu This is my paper

Pith reviewed 2026-06-29 10:19 UTC · model grok-4.3

classification 💻 cs.HC cs.RO
keywords social robotsend-user programminggenerative scaffoldingblock-based programmingnovice programmersLLM assistanceResearch through Design
0
0 comments X

The pith

Robo-Blocks supplies LLM-generated narratives that link novices' high-level ideas to executable social-robot behaviors in a block interface.

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

The paper presents Robo-Blocks, a block-based environment that uses large language models to create structured narratives connecting user ideas to robot actions. Through a Research through Design process and deployment with novices, it identifies emerging user personas and usage patterns. These patterns demonstrate how the scaffolding influences design choices and programming approaches. The work concludes with design insights for incorporating such generative support into social-robot programming without replacing learner effort.

Core claim

Through deployment with novices, the authors discovered emerging user personas and usage patterns for generative scaffolding and showed how this scaffolding shapes end-user design and programming strategies.

What carries the argument

Generative scaffolding: LLM-produced structured narratives that connect high-level ideas to executable robot behaviors inside a block-based editor.

If this is right

  • Novice users adopt distinct personas when interacting with the generative narratives.
  • The scaffolding directly influences the sequence and focus of design and programming decisions.
  • Structured narratives can serve as an intermediate layer between natural-language intent and code blocks.
  • Design guidelines emerge for balancing LLM assistance with opportunities for user ownership.

Where Pith is reading between the lines

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

  • Similar narrative scaffolding could be tested in other end-user domains such as game or IoT scripting to check transfer of the observed patterns.
  • Longer-term studies could track whether repeated exposure to the narratives increases or decreases independent debugging skill.
  • The personas identified may predict which users benefit most from narrative support versus direct code editing.

Load-bearing premise

That LLM-generated structured narratives can reliably connect high-level ideas to executable robot behaviors in a manner that develops rather than supplants novice programming skills.

What would settle it

A controlled comparison in which novices using Robo-Blocks show no measurable gain in ability to create or debug robot programs independently compared with novices using a non-LLM block editor after equivalent practice time.

Figures

Figures reproduced from arXiv: 2605.28154 by Abhinav Maneesh, Arissa J. Sato, Bilge Mutlu, Callie Y. Kim, Hui-Ru Ho, Nathan Thomas White, Yuqing Wang.

Figure 1
Figure 1. Figure 1: The generative scaffolding-based programming paradigm used in [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Robo-Blocks’ interface for the narrative creation phase. Section (a) provides the user with a description of the task. Users can interact using the chat box in section (b) to interact with the LLM agent to create a narrative, using suggestions the agent provides. The user can then mark milestones complete in section (c) or request help from the LLM for a particular milestone. Section (d) provides a descrip… view at source ↗
Figure 3
Figure 3. Figure 3: Robo-Blocks’ interface for the goal generation phase. Users can use section (a) to provide their narrative to the LLM agent. The agent will then convert the story into programmable goals and display them in (b). Hints serve as a secondary layer of scaffolding, further breaking down each programming goal into concrete steps for the user. Depending on the goal, hints may suggest which blocks to use, where to… view at source ↗
Figure 4
Figure 4. Figure 4: Robo-Blocks’ interface for the programming and simulation and testing and deployment phase. Users can build their program in the Blockly canvas (b) using the blocks from the program drawer (a). Users can refer to their goals from the goal generation phase in (e), using the hints as needed to assist in building the program. At any time, users can run their program within the simulator (c) and the robot’s pr… view at source ↗
Figure 5
Figure 5. Figure 5: Study procedure of Robo-Blocks. Participants completed a storyboard activity, then engaged with four phases of Robo-Blocks: narrative creation, goal generation, programming, and deployment, each preceded by a tutorial video. Post-task surveys were completed after narrative creation and after deployment, followed by a post-study survey and semi-structured interview. 4.3 Data Collection Storyboard. Participa… view at source ↗
Figure 6
Figure 6. Figure 6: Three examples of use patterns observed during the programming phase. (a) Dependent: P04 actively followed and [PITH_FULL_IMAGE:figures/full_fig_p010_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Mean and standard deviations of user perceptions [PITH_FULL_IMAGE:figures/full_fig_p011_7.png] view at source ↗
read the original abstract

Programming social robots is challenging for novice robot programmers due to required expertise in planning, interaction design, and programming. While large language models (LLMs) hold significant promise through code generation from natural-language descriptions, they can obscure critical elements of programming and supplant designer intent, eventually resulting in over-reliance instead of developing programming skills. In this paper, we explore how LLM-based social-robot-programming tools can support novice robot programmers through a Research through Design (RtD) process. We designed and prototyped Robo-Blocks, a block-based programming environment that leverages LLMs to offer novice robot programmers generative scaffolding through structured narratives that connect high-level ideas to executable robot behaviors. Through deployment with novices, we discovered emerging user personas and usage patterns for generative scaffolding and showed how this scaffolding shapes end-user design and programming strategies. We present design insights for the effective use of generative scaffolding and its integration into the practice of social-robot programming.

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 / 0 minor

Summary. The paper presents Robo-Blocks, a block-based programming environment that uses LLMs to generate structured narratives as generative scaffolding, connecting high-level ideas to executable robot behaviors for novice social-robot programmers. Through a Research through Design process and a deployment study with novices, the authors report the emergence of user personas and usage patterns, demonstrate how the scaffolding shapes end-user design and programming strategies, and distill design insights for effective integration of such scaffolding.

Significance. If the deployment findings hold, the work offers timely, practice-oriented contributions to HCI and end-user programming by showing how LLM assistance can be structured to support rather than replace novice skills in a complex domain (social-robot interaction design and programming). The persona and pattern discoveries provide concrete, actionable guidance for tool builders; the RtD framing is appropriate for this type of design-knowledge contribution.

major comments (1)
  1. [Deployment section] Deployment section (and abstract): the manuscript states that deployment with novices produced personas, usage patterns, and evidence that scaffolding shapes strategies, yet supplies no information on participant count, recruitment, session protocols, data collection instruments, or analysis methods. These details are load-bearing for the central empirical claims and must be supplied before the strength of the reported discoveries can be assessed.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive feedback. We agree that the methodological details of the deployment study are essential to substantiate the central empirical claims and will provide them in the revision.

read point-by-point responses

  1. Referee: [Deployment section] Deployment section (and abstract): the manuscript states that deployment with novices produced personas, usage patterns, and evidence that scaffolding shapes strategies, yet supplies no information on participant count, recruitment, session protocols, data collection instruments, or analysis methods. These details are load-bearing for the central empirical claims and must be supplied before the strength of the reported discoveries can be assessed.

    Authors: We agree that these details are missing from the current manuscript and are necessary for evaluating the reported findings. In the revised version we will expand the Deployment section with a complete methods description covering participant count, recruitment, session protocols, data collection instruments, and analysis methods, and will update the abstract accordingly to ensure transparency. revision: yes

Circularity Check

0 steps flagged

No significant circularity in qualitative RtD study

full rationale

The paper is a Research through Design study that reports empirical observations of user personas, usage patterns, and strategy shaping from novice deployments of the Robo-Blocks prototype. No equations, fitted parameters, derivations, or mathematical claims exist that could reduce to inputs by construction. Central claims rest on direct study observations rather than self-citation chains, ansatzes, or renamed prior results. This matches the default expectation of no circularity for self-contained qualitative work.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on the domain assumption that structured LLM narratives can usefully bridge high-level intent and executable behavior for novices; no free parameters or invented entities are introduced.

axioms (1)
  • domain assumption LLMs can be leveraged to offer generative scaffolding through structured narratives that connect high-level ideas to executable robot behaviors.
    Explicitly stated in the abstract as the mechanism of the Robo-Blocks tool.

pith-pipeline@v0.9.1-grok · 5716 in / 1228 out tokens · 34286 ms · 2026-06-29T10:19:40.258542+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

85 extracted references · 73 canonical work pages · 1 internal anchor

  1. [1]

    Parastoo Abtahi, Neha Sharma, James A Landay, and Sean Follmer. 2020. Presenting and exploring challenges in human-robot interaction design through bodystorming. InDesign thinking research: Interrogating the doing. Springer, 327–344. https://doi.org/10.1007/978-3-030-62037-0_15

    work page doi:10.1007/978-3-030-62037-0_15 2020

  2. [2]

    Saeema Ahmed, Ken M Wallace, and Lucienne T Blessing. 2003. Understanding the differences between how novice and experienced designers approach design tasks.Research in engineering design14, 1 (2003), 1–11. https://doi.org/10.1007/ s00163-002-0023-z

    2003

  3. [3]

    Gopika Ajaykumar, Maureen Steele, and Chien-Ming Huang. 2021. A Survey on End-User Robot Programming.ACM Comput. Surv.54, 8, Article 164 (Oct. 2021), 36 pages. https://doi.org/10.1145/3466819

    work page doi:10.1145/3466819 2021

  4. [4]

    Caspersen, and Jesper Mosegaard

    Peter Bøgh Andersen, Jens Bennedsen, Steffen Brandorff, Michael E. Caspersen, and Jesper Mosegaard. 2003. Teaching programming to liberal arts students: a narrative media approach.SIGCSE Bull.35, 3 (June 2003), 109–113. https: //doi.org/10.1145/961290.961543

    work page doi:10.1145/961290.961543 2003

  5. [5]

    Andrews, J

    Robert W. Andrews, J. Mason Lilly, Divya Srivastava, and Karen M. Feigh. 2023. The role of shared mental models in human-AI teams: a theoretical review.Theo- retical Issues in Ergonomics Science24, 2 (2023), 129–175. https://doi.org/10.1080/ 1463922X.2022.2061080 arXiv:https://doi.org/10.1080/1463922X.2022.2061080

    work page doi:10.1080/1463922x.2022.2061080 2023

  6. [6]

    Calderita, Pablo Bustos, and Luis J

    Pilar Bachiller-Burgos, Iván Barbecho, Luis V. Calderita, Pablo Bustos, and Luis J. Manso. 2020. LearnBlock: A Robot-Agnostic Educational Programming Tool. IEEE Access8 (2020), 30012–30026. https://doi.org/10.1109/ACCESS.2020.2972410

    work page doi:10.1109/access.2020.2972410 2020

  7. [7]

    Linden J Ball, J St BT Evans, and Ian Dennis. 1994. Cognitive processes in engineering design: A longitudinal study.Ergonomics37, 11 (1994), 1753–1786. https://doi.org/10.1080/00140139408964950

    work page doi:10.1080/00140139408964950 1994

  8. [8]

    Sara Beschi, Daniela Fogli, and Fabio Tampalini. 2019. CAPIRCI: A Multi-modal System for Collaborative Robot Programming. InEnd-User Development, Alessio Malizia, Stefano Valtolina, Anders Morch, Alan Serrano, and Andrew Stratton (Eds.). Springer International Publishing, Cham, 51–66. https://doi.org/10.1007/ 978-3-030-24781-2_4

    2019

  9. [9]

    Cynthia Breazeal. 2003. Toward sociable robots.Robotics and Autonomous Systems 42, 3 (2003), 167–175. https://doi.org/10.1016/S0921-8890(02)00373-1 Socially Interactive Robots

    work page doi:10.1016/s0921-8890(02)00373-1 2003

  10. [10]

    John Brooke et al. 1996. SUS-A quick and dirty usability scale.Usability evaluation in industry189, 194 (1996), 4–7. Robo-Blocks: Generative Scaffolding in End-User Design and Programming of Social Robots DIS ’26, June 13–17, 2026, Singapore, Singapore

    1996

  11. [11]

    Bruce G Buchanan and Reid G Smith. 1988. Fundamentals of expert systems. Annual review of computer science3, 1 (1988), 23–58

    1988

  12. [12]

    Nina Buchina, Sherin Kamel, and Emilia Barakova. 2016. Design and evaluation of an end-user friendly tool for robot programming. In2016 25th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)(New York, NY, USA). IEEE Press, 185–191. https://doi.org/10.1109/ROMAN.2016. 7745109

    work page doi:10.1109/roman.2016 2016

  13. [13]

    Carroll and Judith Reitman Olson

    John M. Carroll and Judith Reitman Olson. 1988. Chapter 2 - Mental Models in Human-Computer Interaction11This chapter appeared in its entirety and is reprinted from Mental Models in Human Computer Interaction: Research Issues about What the User of Software Knows, J.M. Carroll and J.R. Olson, Editors,-The report of the workshop on software human factors: ...

    work page doi:10.1016/b978-0-444-70536-5.50007-5 1988

  14. [14]

    Juo-Tung Chen and Chien-Ming Huang. 2024. Forgetful Large Language Models: Lessons Learned from Using LLMs in Robot Programming.Proceedings of the AAAI Symposium Series2, 1 (Jan. 2024), 508–513. https://doi.org/10.1609/aaaiss. v2i1.27721

    work page doi:10.1609/aaaiss 2024

  15. [15]

    Aparajita Chowdhury, Aino Ahtinen, Roel Pieters, and Kaisa Vaananen. 2020. User Experience Goals for Designing Industrial Human-Cobot Collaboration: A Case Study of Franka Panda Robot. InProceedings of the 11th Nordic Conference on Human-Computer Interaction: Shaping Experiences, Shaping Society(Tallinn, Estonia)(NordiCHI ’20). Association for Computing M...

    work page doi:10.1145/3419249.3420161 2020

  16. [16]

    Victoria Clarke and Virginia Braun. 2017. Thematic analysis.The Journal of Positive Psychology12, 3 (2017), 297–298. https://doi.org/10.1080/17439760.2016. 1262613

    work page doi:10.1080/17439760.2016 2017

  17. [17]

    Sarah Fakhoury, Aaditya Naik, Georgios Sakkas, Saikat Chakraborty, and Shuvendu K. Lahiri. 2024. LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation.IEEE Transactions on Software Engineering 50, 9 (2024), 2254–2268. https://doi.org/10.1109/TSE.2024.3428972

    work page doi:10.1109/tse.2024.3428972 2024

  18. [18]

    Terrence Fong, Illah Nourbakhsh, and Kerstin Dautenhahn. 2003. A survey of socially interactive robots.Robotics and Autonomous Systems42, 3 (2003), 143–166. https://doi.org/10.1016/S0921-8890(02)00372-X Socially Interactive Robots

    work page doi:10.1016/s0921-8890(02)00372-x 2003

  19. [19]

    Neil Fraser. 2015. Ten things we’ve learned from Blockly. InProceedings of the 2015 IEEE Blocks and Beyond Workshop (Blocks and Beyond) (BLOCKS AND BEYOND ’15). IEEE Computer Society, USA, 49–50. https://doi.org/10.1109/BLOCKS.2015. 7369000

    work page doi:10.1109/blocks.2015 2015

  20. [20]

    Zichao Hu, Francesca Lucchetti, Claire Schlesinger, Yash Saxena, Anders Freeman, Sadanand Modak, Arjun Guha, and Joydeep Biswas. 2024. Deploying and Evaluating LLMs to Program Service Mobile Robots.IEEE Robotics and Automation Letters9, 3 (2024), 2853–2860. https://doi.org/10.1109/LRA.2024. 3360020

    work page doi:10.1109/lra.2024 2024

  21. [21]

    Justin Huang and Maya Cakmak. 2017. Code3: A System for End-to-End Programming of Mobile Manipulator Robots for Novices and Experts. In Proceedings of the 2017 ACM/IEEE International Conference on Human-Robot Interaction(Vienna, Austria)(HRI ’17). Association for Computing Machinery, New York, NY, USA, 453–462. https://doi.org/10.1145/2909824.3020215

    work page doi:10.1145/2909824.3020215 2017

  22. [22]

    Justin Huang, Tessa Lau, and Maya Cakmak. 2016. Design and Evaluation of a Rapid Programming System for Service Robots. InThe Eleventh ACM/IEEE International Conference on Human Robot Interaction(Christchurch, New Zealand) (HRI ’16). IEEE Press, 295–302

    2016

  23. [23]

    Oliver Huang, Muhammad Fatir, Steven Luo, Sangho Suh, Hariharan Subra- monyam, and Carolina Nobre. 2026. Narrative Scaffolding: A Narrative-First Framework for Data-Driven Sensemaking. arXiv:2512.18920 [cs.HC] https: //arxiv.org/abs/2512.18920

    work page arXiv 2026

  24. [24]

    Yohan Hwang and Jang Ho Lee. 2025. Exploring students’ experiences and perceptions of human-AI collaboration in digital content making.International Journal of Educational Technology in Higher Education22 (07 2025). https: //doi.org/10.1186/s41239-025-00542-0

    work page doi:10.1186/s41239-025-00542-0 2025

  25. [25]

    Bryce Ikeda and Daniel Szafir. 2024. PRogramAR: Augmented Reality End-User Robot Programming.J. Hum.-Robot Interact.13, 1, Article 15 (March 2024), 20 pages. https://doi.org/10.1145/3640008

    work page doi:10.1145/3640008 2024

  26. [26]

    Durgaprasad Janjanam, Bharathi Ganesh, and L Manjunatha. 2021. Design of an expert system architecture: An overview.Journal of Physics: Conference Series 1767, 1 (feb 2021), 012036. https://doi.org/10.1088/1742-6596/1767/1/012036

    work page doi:10.1088/1742-6596/1767/1/012036 2021

  27. [27]

    Hongye Jin, Xiaotian Han, Jingfeng Yang, Zhimeng Jiang, Zirui Liu, Chia-Yuan Chang, Huiyuan Chen, and Xia Hu. 2024. Llm maybe longlm: Self-extend llm context window without tuning.arXiv preprint arXiv:2401.01325(2024)

    work page arXiv 2024

  28. [28]

    Michal Kapinus, Vítězslav Beran, Zdeněk Materna, and Daniel Bambušek. 2019. Spatially Situated End-User Robot Programming in Augmented Reality. In2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)(New Delhi, India). IEEE Press, 1–8. https://doi.org/10.1109/RO- MAN46459.2019.8956336

    work page doi:10.1109/ro- 2019

  29. [29]

    Ulas Berk Karli, Juo-Tung Chen, Victor Nikhil Antony, and Chien-Ming Huang

  30. [30]

    Kim, Christine P

    Alchemist: LLM-Aided End-User Development of Robot Applications. InProceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction(Boulder, CO, USA)(HRI ’24). Association for Computing Machinery, New York, NY, USA, 361–370. https://doi.org/10.1145/3610977.3634969

    work page doi:10.1145/3610977.3634969 2024

  31. [31]

    Majeed Kazemitabaar, Xinying Hou, Austin Henley, Barbara Jane Ericson, David Weintrop, and Tovi Grossman. 2024. How Novices Use LLM-based Code Generators to Solve CS1 Coding Tasks in a Self-Paced Learning Environment. InProceedings of the 23rd Koli Calling International Conference on Computing Education Research(Koli, Finland)(Koli Calling ’23). Associati...

    work page arXiv 2024

  32. [32]

    Majeed Kazemitabaar, Runlong Ye, Xiaoning Wang, Austin Zachary Henley, Paul Denny, Michelle Craig, and Tovi Grossman. 2024. CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). As...

    work page doi:10.1145/3613904.3642773 2024

  33. [33]

    Kim, Christine P

    Callie Y. Kim, Christine P. Lee, and Bilge Mutlu. 2024. Understanding Large- Language Model (LLM)-powered Human-Robot Interaction. InProceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction(Boulder, CO, USA)(HRI ’24). Association for Computing Machinery, New York, NY, USA, 371–380. https://doi.org/10.1145/3610977.3634966

    work page doi:10.1145/3610977.3634966 2024

  34. [34]

    Kim, Nathan Thomas White, Evan He, Frederic Sala, and Bilge Mutlu

    Callie Y. Kim, Nathan Thomas White, Evan He, Frederic Sala, and Bilge Mutlu

  35. [35]

    InProceedings of the 21st ACM/IEEE Inter- national Conference on Human-Robot Interaction(Edinburgh, Scotland, UK) (HRI ’26)

    RoboCritics: Enabling Reliable End-to-End LLM Robot Programming through Expert-Informed Critics. InProceedings of the 21st ACM/IEEE Inter- national Conference on Human-Robot Interaction(Edinburgh, Scotland, UK) (HRI ’26). Association for Computing Machinery, New York, NY, USA, 914–923. https://doi.org/10.1145/3757279.3785550

    work page doi:10.1145/3757279.3785550

  36. [36]

    Kheng Lee Koay, Dag Sverre Syrdal, Kerstin Dautenhahn, and Michael L. Walters. 2020. A narrative approach to human-robot interaction prototyping for companion robots.Paladyn, Journal of Behavioral Robotics11, 1 (2020), 66–85. https://doi.org/10.1515/PJBR-2020-0003

    work page doi:10.1515/pjbr-2020-0003 2020

  37. [37]

    Amy Koike, Bengisu Cagiltay, and Bilge Mutlu. 2024. Tangible Scenography as a Holistic Design Method for Human-Robot Interaction. InProceedings of the 2024 ACM Designing Interactive Systems Conference(Copenhagen, Denmark) (DIS ’24). Association for Computing Machinery, New York, NY, USA, 459–475. https://doi.org/10.1145/3643834.3661530

    work page doi:10.1145/3643834.3661530 2024

  38. [38]

    Liang, Chenyang Yang, and Brad A

    Jenny T. Liang, Chenyang Yang, and Brad A. Myers. 2023. A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges. arXiv:2303.17125 [cs.SE] https://arxiv.org/abs/2303.17125

    work page arXiv 2023

  39. [39]

    Jinfang Liu, Yi Zhang, Wei Li, Qiyun Wang, Pingxiu Niu, and Xue Zhang. 2026. Adaptive vs. planned metacognitive scaffolding for computational thinking: Evidence from generative AI-supported programming in elementary education. Computers & Education241 (2026), 105473. https://doi.org/10.1016/j.compedu. 2025.105473

    work page doi:10.1016/j.compedu 2026

  40. [40]

    Zhicheng Liu and John Stasko. 2010. Mental Models, Visual Reasoning and Interaction in Information Visualization: A Top-down Perspective.IEEE Transactions on Visualization and Computer Graphics16, 6 (2010), 999–1008. https://doi.org/10.1109/TVCG.2010.177

    work page doi:10.1109/tvcg.2010.177 2010

  41. [41]

    Arnold Lund. 2001. Measuring Usability with the USE Questionnaire.Usability and User Experience Newsletter of the STC Usability SIG8 (01 2001)

    2001

  42. [42]

    Michal Luria, Marius Hoggenmüller, Wen-Ying Lee, Luke Hespanhol, Malte Jung, and Jodi Forlizzi. 2021. Research through Design Approaches in Human-Robot Interaction. InCompanion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction(Boulder, CO, USA)(HRI ’21 Companion). Association for Computing Machinery, New York, NY, USA, 685–687. http...

    work page arXiv 2021

  43. [43]

    Boxuan Ma, Huiyong Li, Gen Li, Li Chen, Cheng Tang, Yinjie Xie, Chenghao Gu, Atsushi Shimada, and Shin’ichi Konomi. 2025. Scaffolding Metacognition in Programming Education: Understanding Student-AI Interactions and Design Implications. arXiv:2511.04144 [cs.HC] https://arxiv.org/abs/2511.04144

    work page arXiv 2025

  44. [44]

    Shuai Ma, Junling Wang, Yuanhao Zhang, Xiaojuan Ma, and April Yi Wang. 2025. DBox: Scaffolding Algorithmic Programming Learning through Learner-LLM Co-Decomposition. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Machinery, New York, NY, USA, Article 585, 20 pages. https://doi.org/10.114...

    work page doi:10.1145/3706598.3713748 2025

  45. [45]

    Karthik Mahadevan, Jonathan Chien, Noah Brown, Zhuo Xu, Carolina Parada, Fei Xia, Andy Zeng, Leila Takayama, and Dorsa Sadigh. 2024. Generative Expressive Robot Behaviors using Large Language Models. InProceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction(Boulder, CO, USA)(HRI ’24). Association for Computing Machinery, New Y...

    work page doi:10.1145/3610977.3634999 2024

  46. [46]

    Karthik Mahadevan, Blaine Lewis, Jiannan Li, Bilge Mutlu, Anthony Tang, and Tovi Grossman. 2025. ImageInThat: Manipulating Images to Convey User Instructions to Robots. In2025 20th ACM/IEEE International Conference on Human-Robot Interaction (HRI). 757–766. https://doi.org/10.1109/HRI61500.2025. DIS ’26, June 13–17, 2026, Singapore, Singapore Sato et al. 10974179

    work page doi:10.1109/hri61500.2025 2025

  47. [47]

    Mason, Karen R

    Linda H. Mason, Karen R. Harris, and Steve Graham. 2002. Every Child Has a Story to Tell: Self-Regulated Strategy Development for Story Writing.Education and Treatment of Children25, 4 (2002), 496–506. http://www.jstor.org/stable/42899724

    work page arXiv 2002

  48. [48]

    Christoph Mayr-Dorn, Mario Winterer, Christian Salomon, Doris Hohensinger, and Rudolf Ramler. 2021. Considerations for using Block-Based Languages for Industrial Robot Programming - a Case Study. In2021 IEEE/ACM 3rd International Workshop on Robotics Software Engineering (RoSE). IEEE, 5–12. https://doi.org/ 10.1109/RoSE52553.2021.00008

    work page doi:10.1109/rose52553.2021.00008 2021

  49. [49]

    Roger McDermott, Gordon Eccleston, and Garry Brindley. 2008. More than a good story — can you really teach programming through story- telling?Innovation in Teaching and Learning in Information and Computer Sciences7, 1 (2008), 34–43. https://doi.org/10.11120/ital.2008.07010034 arXiv:https://doi.org/10.11120/ital.2008.07010034

    work page doi:10.11120/ital.2008.07010034 2008

  50. [50]

    Monika Mladenović, Ivica Boljat, and Žana Žanko. 2018. Comparing loops misconceptions in block-based and text-based programming languages at the K-12 level.Education and Information Technologies23 (2018), 1483–1500. https: //doi.org/10.1007/s10639-017-9673-3

    work page doi:10.1007/s10639-017-9673-3 2018

  51. [51]

    Github copilot AI pair programmer: Asset or liability? J

    Arghavan Moradi Dakhel, Vahid Majdinasab, Amin Nikanjam, Foutse Khomh, Michel C. Desmarais, and Zhen Ming (Jack) Jiang. 2023. GitHub Copilot AI pair programmer: Asset or Liability?Journal of Systems and Software203 (2023), 111734. https://doi.org/10.1016/j.jss.2023.111734

    work page doi:10.1016/j.jss.2023.111734 2023

  52. [52]

    Sílvia Moros, Luke Wood, Ben Robins, Kerstin Dautenhahn, and Álvaro Castro-González. 2020. Programming a Humanoid Robot with the Scratch Language. InRobotics in Education, Munir Merdan, Wilfried Lepuschitz, Gottfried Koppensteiner, Richard Balogh, and David Obdržálek (Eds.). Springer International Publishing, Cham, 222–233. https://doi.org/10.1007/978-3-0...

    work page doi:10.1007/978-3-030- 2020

  53. [53]

    Daye Nam, Andrew Macvean, Vincent Hellendoorn, Bogdan Vasilescu, and Brad Myers. 2024. Using an LLM to Help With Code Understanding. InProceedings of the IEEE/ACM 46th International Conference on Software Engineering(Lisbon, Portugal)(ICSE ’24). Association for Computing Machinery, New York, NY, USA, Article 97, 13 pages. https://doi.org/10.1145/3597503.3639187

    work page doi:10.1145/3597503.3639187 2024

  54. [54]

    Akhil Padmanabha, Jessie Yuan, Janavi Gupta, Zulekha Karachiwalla, Carmel Majidi, Henny Admoni, and Zackory Erickson. 2024. VoicePilot: Harnessing LLMs as Speech Interfaces for Physically Assistive Robots. InProceedings of the 37th Annual ACM Symposium on User Interface Software and Technology(Pittsburgh, PA, USA)(UIST ’24). Association for Computing Mach...

    work page doi:10.1145/3654777.3676401 2024

  55. [55]

    Jennifer Parham-Mocello and Martin Erwig. 2020. Does Story Programming Prepare for Coding?. InProceedings of the 51st ACM Technical Symposium on Computer Science Education(Portland, OR, USA)(SIGCSE ’20). Association for Computing Machinery, New York, NY, USA, 100–106. https://doi.org/10.1145/ 3328778.3366861

    work page arXiv 2020

  56. [56]

    David Porfirio, Evan Fisher, Allison Sauppé, Aws Albarghouthi, and Bilge Mutlu

  57. [57]

    InProceedings of the 32nd Annual ACM Symposium on User Interface Software and Technology(New Orleans, LA, USA)(UIST ’19)

    Bodystorming Human-Robot Interactions. InProceedings of the 32nd Annual ACM Symposium on User Interface Software and Technology(New Orleans, LA, USA)(UIST ’19). Association for Computing Machinery, New York, NY, USA, 479–491. https://doi.org/10.1145/3332165.3347957

    work page doi:10.1145/3332165.3347957

  58. [58]

    Porfirio, Laura Stegner, Maya Cakmak, Allison Sauppé, Aws Albargh- outhi, and Bilge Mutlu

    David J. Porfirio, Laura Stegner, Maya Cakmak, Allison Sauppé, Aws Albargh- outhi, and Bilge Mutlu. 2021. Figaro: A Tabletop Authoring Environment for Human-Robot Interaction. InProceedings of the 2021 CHI Conference on Human Factors in Computing Systems(Yokohama, Japan)(CHI ’21). Association for Computing Machinery, New York, NY, USA, Article 414, 15 pag...

    work page doi:10.1145/3411764.3446864 2021

  59. [59]

    E. Pot, J. Monceaux, R. Gelin, and B. Maisonnier. 2009. Choregraphe: a graphical tool for humanoid robot programming. InRO-MAN 2009 - The 18th IEEE International Symposium on Robot and Human Interactive Communication. IEEE, 46–51. https://doi.org/10.1109/ROMAN.2009.5326209

    work page doi:10.1109/roman.2009.5326209 2009

  60. [60]

    Muhammet Ramoğlu, Çağlar Genç, and Kerem Rızvanoğlu. 2017. Programming a Robotic Toy with a Block Coding Application: A Usability Study with Non-programmer Adults. InDesign, User Experience, and Usability: Theory, Methodology, and Management, Aaron Marcus and Wentao Wang (Eds.). Springer International Publishing, Cham, 652–666

    2017

  61. [61]

    Mitchel Resnick, John Maloney, Andrés Monroy-Hernández, Natalie Rusk, Evelyn Eastmond, Karen Brennan, Amon Millner, Eric Rosenbaum, Jay Silver, Brian Silverman, and Yasmin Kafai. 2009. Scratch: programming for all.Commun. ACM 52, 11 (Nov. 2009), 60–67. https://doi.org/10.1145/1592761.1592779

    work page doi:10.1145/1592761.1592779 2009

  62. [62]

    Kristin Y. Rozier. 2011. Linear Temporal Logic Symbolic Model Checking. Computer Science Review5, 2 (2011), 163–203. https://doi.org/10.1016/j.cosrev. 2010.06.002

    work page doi:10.1016/j.cosrev 2011

  63. [63]

    Kimiko Ryokai, Michael Jongseon Lee, and Jonathan Micah Breitbart. 2009. Children’s storytelling and programming with robotic characters. InProceedings of the Seventh ACM Conference on Creativity and Cognition(Berkeley, California, USA)(C&C ’09). Association for Computing Machinery, New York, NY, USA, 19–28. https://doi.org/10.1145/1640233.1640240

    work page doi:10.1145/1640233.1640240 2009

  64. [64]

    David Adrian Sanders, Alexander Gegov, and David Ndzi. 2018. Knowledge-Based Expert System Using a Set of Rules to Assist a Tele-operated Mobile Robot. In Intelligent Systems and Applications, Yaxin Bi, Supriya Kapoor, and Rahul Bhatia (Eds.). Springer International Publishing, Cham, 371–392

    2018

  65. [65]

    Mike Scaife and Yvonne Rogers. 1996. External cognition: how do graphical representations work?International Journal of Human-Computer Studies45, 2 (1996), 185–213. https://doi.org/10.1006/ijhc.1996.0048

    work page doi:10.1006/ijhc.1996.0048 1996

  66. [66]

    Dennis Schleicher, Peter Jones, and Oksana Kachur. 2010. Bodystorming as embodied designing.Interactions17, 6 (Nov. 2010), 47–51. https://doi.org/10. 1145/1865245.1865256

    work page arXiv 2010

  67. [67]

    Andrew Schoen, Curt Henrichs, Mathias Strohkirch, and Bilge Mutlu. 2020. Authr: A Task Authoring Environment for Human-Robot Teams. InProceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology(Virtual Event, USA)(UIST ’20). Association for Computing Machinery, New York, NY, USA, 1194–1208. https://doi.org/10.1145/3379337.3415872

    work page doi:10.1145/3379337.3415872 2020

  68. [68]

    Andrew Schoen and Bilge Mutlu. 2024. OpenVP: A Customizable Visual Programming Environment for Robotics Applications. InProceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction(Boulder, CO, USA)(HRI ’24). Association for Computing Machinery, New York, NY, USA, 944–948. https://doi.org/10.1145/3610977.3637477

    work page doi:10.1145/3610977.3637477 2024

  69. [69]

    Andrew Schoen, Nathan White, Curt Henrichs, Amanda Siebert-Evenstone, David Shaffer, and Bilge Mutlu. 2022. CoFrame: A System for Training Novice Cobot Programmers. In2022 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI). IEEE Press, 185–194. https://doi.org/10.1109/HRI53351.2022. 9889345

    work page doi:10.1109/hri53351.2022 2022

  70. [70]

    Preciado Vanegas, and Kim Baraka

    Nienke Schrage-Prent, Daniel F. Preciado Vanegas, and Kim Baraka. 2024. Interactive Robot Programming Inspired by Dog Training: An Exploratory Study. InCompanion Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction(Boulder, CO, USA)(HRI Companion ’24). Association for Computing Machinery, New York, NY, USA, 965–969. https:/...

    work page arXiv 2024

  71. [71]

    Sefidgar, Thomas Weng, Heather Harvey, Sarah Elliott, and Maya Cakmak

    Yasaman S. Sefidgar, Thomas Weng, Heather Harvey, Sarah Elliott, and Maya Cakmak. 2018. RobotIST: Interactive Situated Tangible Robot Programming. InProceedings of the 2018 ACM Symposium on Spatial User Interaction(Berlin, Germany)(SUI ’18). Association for Computing Machinery, New York, NY, USA, 141–149. https://doi.org/10.1145/3267782.3267921

    work page doi:10.1145/3267782.3267921 2018

  72. [72]

    Peng Shu, Huaqin Zhao, Hanqi Jiang, Yiwei Li, Shaochen Xu, Yi Pan, Zihao Wu, Zhengliang Liu, Guoyu Lu, Le Guan, Gong Chen, and Xianqiao Wang Tianming Liu. 2024. LLMs for Coding and Robotics Education. arXiv:2402.06116 [cs.RO] https://arxiv.org/abs/2402.06116

    work page arXiv 2024

  73. [73]

    Vemprala, Rogerio Bonatti, Arthur Bucker, and Ashish Kapoor

    Sai H. Vemprala, Rogerio Bonatti, Arthur Bucker, and Ashish Kapoor. 2024. ChatGPT for Robotics: Design Principles and Model Abilities.IEEE Access12 (2024), 55682–55696. https://doi.org/10.1109/ACCESS.2024.3387941

    work page doi:10.1109/access.2024.3387941 2024

  74. [74]

    Shepherd, and Diana Franklin

    David Weintrop, Afsoon Afzal, Jean Salac, Patrick Francis, Boyang Li, David C. Shepherd, and Diana Franklin. 2018. Evaluating CoBlox: A Comparative Study of Robotics Programming Environments for Adult Novices. InProceedings of the 2018 CHI Conference on Human Factors in Computing Systems(Montreal QC, Canada)(CHI ’18). Association for Computing Machinery, ...

    work page doi:10.1145/3173574.3173940 2018

  75. [75]

    Shepherd, Patrick Francis, and Diana Franklin

    David Weintrop, David C. Shepherd, Patrick Francis, and Diana Franklin. 2017. Blockly goes to work: Block-based programming for industrial robots. In2017 IEEE Blocks and Beyond Workshop (B&B). 29–36. https://doi.org/10.1109/BLOCKS. 2017.8120406

    work page doi:10.1109/blocks 2017

  76. [76]

    David Weintrop and Uri Wilensky. 2015. To block or not to block, that is the question: students’ perceptions of blocks-based programming. InProceedings of the 14th International Conference on Interaction Design and Children(Boston, Massachusetts)(IDC ’15). Association for Computing Machinery, New York, NY, USA, 199–208. https://doi.org/10.1145/2771839.2771860

    work page doi:10.1145/2771839.2771860 2015

  77. [77]

    David Weintrop and Uri Wilensky. 2017. Comparing Block-Based and Text-Based Programming in High School Computer Science Classrooms.ACM Trans. Comput. Educ.18, 1, Article 3 (Oct. 2017), 25 pages. https://doi.org/10.1145/3089799

    work page doi:10.1145/3089799 2017

  78. [78]

    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

  79. [79]

    Neural Informed RRT*: Learning-based path planning with point cloud state representations under admissible ellipsoidal constraints,

    Ziyi Yang, Shreyas S. Raman, Ankit Shah, and Stefanie Tellex. 2024. Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents. In2024 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 14435–14442. https://doi.org/10.1109/ICRA57147.2024.10611447

    work page doi:10.1109/icra57147.2024.10611447 2024

  80. [80]

    Ryan Yen, Jiawen Stefanie Zhu, Sangho Suh, Haijun Xia, and Jian Zhao. 2024. CoLadder: Manipulating Code Generation via Multi-Level Blocks. InProceedings of the 37th Annual ACM Symposium on User Interface Software and Technology (Pittsburgh, PA, USA)(UIST ’24). Association for Computing Machinery, New York, NY, USA, Article 11, 20 pages. https://doi.org/10...

    work page doi:10.1145/3654777.3676357 2024

Showing first 80 references.