pith. machine review for the scientific record. sign in

arxiv: 2604.19114 · v1 · submitted 2026-04-21 · 💻 cs.HC

Recognition: unknown

OOPrompt: Reifying Intents into Structured Artifacts for Modular and Iterative Prompting

Tengyou Xu , Detao Ma , Xiang 'Anthony' Chen
Authors on Pith no claims yet

Pith reviewed 2026-05-10 02:26 UTC · model grok-4.3

classification 💻 cs.HC
keywords prompt engineeringlarge language modelshuman-computer interactionobject-oriented promptingstructured artifactsiterative designmodular interfaces
0
0 comments X

The pith

OOPrompt turns user intents into structured, manipulable prompt objects instead of linear text strings.

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

The paper presents Object-Oriented Prompting as a way to handle complex, multifaceted intents when working with large language models. Instead of writing prompts as unbroken text, users build them from editable artifacts that can be created, combined, revised, and reused like program objects. This unifies several existing prompting techniques under one interaction model. The authors derive the approach from a design space analysis, test it in a formative study with 20 participants, refine it, and then validate the full prototype. A reader would care because the method directly addresses the practical difficulty of composing and maintaining sophisticated LLM instructions over time.

Core claim

By reifying user intents into structured artifacts, OOPrompt enables modular creation, editing, iteration, and reuse of prompts, unifying and generalizing prior point systems for prompt-based LLM interaction. The design space supports this through object-like properties that make intents explicit and manipulable rather than implicit in linear text.

What carries the argument

Object-Oriented Prompting (OOPrompt) paradigm that reifies intents into structured, manipulable artifacts.

If this is right

  • Complex prompts can be decomposed into independent, reusable components rather than rewritten from scratch each time.
  • Existing techniques such as chain-of-thought or few-shot examples can be encapsulated as distinct object types within the same framework.
  • Prompt-based systems gain a consistent way to support iteration on specific intent facets without disrupting the whole prompt.
  • Designers of LLM interfaces obtain a unified design space that generalizes multiple ad-hoc prompting methods.

Where Pith is reading between the lines

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

  • The same object model could be applied to other generative interfaces, such as image or code generators, where intents are similarly multifaceted.
  • Shared libraries of prompt objects might enable collaboration or version control practices that are currently difficult with plain text prompts.
  • Future LLM tools could incorporate visual editors that treat prompts as draggable, connectable components, resembling low-code environments.

Load-bearing premise

The benefits observed in the formative study with 20 participants and the subsequent validation study generalize beyond the specific prototype and participant pool to broader prompt-based LLM systems.

What would settle it

A larger, more diverse user study that finds no measurable gain in prompt composition speed, accuracy, or satisfaction when participants use structured OOPrompt artifacts versus conventional linear text prompts.

Figures

Figures reproduced from arXiv: 2604.19114 by Detao Ma, Tengyou Xu, Xiang 'Anthony' Chen.

Figure 1
Figure 1. Figure 1: Overview of research process for developing Object-Oriented Prompting ( [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: The initial design space of OOPrompt, outlining the [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: The OOPrompt MVP workflow with a simple walkthrough example about trip planning. The diagram illustrates the end-to-end process of how user can interact with the interface, from initializing a prompt via templates or free-text input (A), through structuring and refining intent properties (B), to generating a final deployable prompt in natural language, JSON, or hybrid form (C). The example on the right dem… view at source ↗
Figure 4
Figure 4. Figure 4: The final design space of OOPrompt updated by insights gathered through the formative study. This illustrates the [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: The OOPrompt system pipeline and underlying data structure. (A) Initialization: A raw natural language intent is reified into a base Prompt Object. (B) Property Definition: Abstract attributes are encapsulated into Property Objects with specific states like emphasis and examples. (C) Hierarchical Structure: Users manage complexity through nested organization, where a property can instantiate a child Prompt… view at source ↗
Figure 6
Figure 6. Figure 6: An example showing the differences between the task settings in formative study and validation study. The formative [PITH_FULL_IMAGE:figures/full_fig_p015_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Example implementation of an improved OOPrompt workflow that autonomously calls multiple LLM assistants in parallel. After the user submits the raw input, the system simultaneously extracts properties and generates corresponding examples and modification suggestions within the same step. All results are produced automatically without additional user activation and are presented as options for selective app… view at source ↗
read the original abstract

The rise of large language models (LLMs) has given rise to a class of prompt-based interactive systems where users primarily express their input in natural language. However, composing a prompt as a linear text string becomes unwieldy when capturing users' multifaceted intents. We present Object-Oriented Prompting (OOPrompt), an emergent interaction paradigm that enables users to create, edit, iterate, and reuse prompts as structured, manipulable artifacts, unifying and generalizing several existing point systems. We first outlined a design space from existing work and built an early prototype, which we deployed as a probe in a formative study with 20 participants. Their feedback informed an expanded OOPrompt design space. We then developed the full OOPrompt prototype and conducted a validation study to further understand OOPrompt's added values and trade-offs. We expect the OOPrompt design space to provide theoretical and empirical guidance to the design and engineering of prompt-based, LLM-enabled interactive systems.

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

2 major / 2 minor

Summary. The manuscript introduces Object-Oriented Prompting (OOPrompt) as an interaction paradigm that reifies user intents into structured, manipulable artifacts rather than linear text strings. It derives an initial design space from existing prompting systems, deploys an early prototype in a formative study with 20 participants, expands the design space based on feedback, implements a full prototype, and conducts a validation study to assess added values (modularity, iteration, reuse) and trade-offs, claiming to unify and generalize prior point systems while providing theoretical and empirical guidance for prompt-based LLM interfaces.

Significance. If the validation study's evidence for benefits holds under scrutiny, OOPrompt could meaningfully advance HCI for LLM systems by offering a coherent framework that addresses the scalability limits of linear prompting. The design space and iterative prototype development represent a constructive contribution that could guide engineering of future tools, particularly where complex, multi-faceted intents must be expressed and refined.

major comments (2)
  1. [Validation study] Validation study section: The manuscript provides no details on the study design, participant demographics or recruitment, specific tasks or prompts used, quantitative or qualitative measures of 'added value' and trade-offs (e.g., how modularity or reuse were operationalized and scored), statistical analysis, or controls for confounds such as prototype familiarity. These omissions are load-bearing because the central claims about unification, generalization, and practical benefits rest directly on the outcomes of this study.
  2. [Discussion] Discussion or implications section: The assertion that OOPrompt unifies existing systems and that observed benefits transfer beyond the single prototype and participant pool lacks supporting analysis or explicit limitations discussion. The formative study (n=20) and validation study are tied to an iteratively refined prototype whose design space was shaped by the same participants; without evidence or argumentation for transfer to other interfaces, models, or task distributions, the generalization claim cannot be evaluated.
minor comments (2)
  1. [Abstract] Abstract: The summary of the two studies is too high-level; adding one sentence on key measures or findings would improve standalone readability without lengthening the abstract excessively.
  2. [Design space] Design space description: Provide concrete examples of how participant feedback from the formative study directly altered specific dimensions of the expanded design space (e.g., new artifact types or manipulation operations).

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive and detailed feedback, which identifies key areas where our reporting and argumentation can be strengthened. We address each major comment below and will revise the manuscript to improve transparency and balance in our claims.

read point-by-point responses

  1. Referee: [Validation study] Validation study section: The manuscript provides no details on the study design, participant demographics or recruitment, specific tasks or prompts used, quantitative or qualitative measures of 'added value' and trade-offs (e.g., how modularity or reuse were operationalized and scored), statistical analysis, or controls for confounds such as prototype familiarity. These omissions are load-bearing because the central claims about unification, generalization, and practical benefits rest directly on the outcomes of this study.

    Authors: We agree that the validation study section lacks the necessary detail for readers to fully evaluate the results. The study was executed with a complete protocol, but space constraints led to an abbreviated presentation. In the revised manuscript we will expand this section to describe the full study design, participant recruitment method and demographics, the specific tasks and example prompts used, how modularity, iteration, and reuse were operationalized and scored (both quantitatively and qualitatively), the statistical tests performed, and controls such as counterbalancing and training procedures. We will also include key results tables and representative qualitative excerpts. This revision will make the empirical support for our claims verifiable. revision: yes

  2. Referee: [Discussion] Discussion or implications section: The assertion that OOPrompt unifies existing systems and that observed benefits transfer beyond the single prototype and participant pool lacks supporting analysis or explicit limitations discussion. The formative study (n=20) and validation study are tied to an iteratively refined prototype whose design space was shaped by the same participants; without evidence or argumentation for transfer to other interfaces, models, or task distributions, the generalization claim cannot be evaluated.

    Authors: We accept that the current discussion does not provide sufficient analysis or limitations to support the unification and generalization statements. The unification claim originates primarily from the initial design space derived from prior prompting literature, with the studies serving as validation rather than the sole basis. Nevertheless, we agree the text requires explicit mapping and a limitations discussion. In revision we will add (1) an analysis that explicitly maps OOPrompt elements to representative prior systems and (2) a dedicated limitations subsection addressing the prototype-specific nature of the findings, the role of the formative study in shaping the design space, participant characteristics, and the absence of direct evidence for transfer across interfaces, models, or task domains. We will also qualify the language around generalization to reflect these boundaries while retaining the design space as the primary generalizable contribution. revision: yes

Circularity Check

0 steps flagged

No circularity: design-study paper with independent empirical grounding

full rationale

The paper presents OOPrompt as an interaction paradigm derived from an initial design space taken from prior external literature, refined via a formative study (n=20), then validated in a second study. No equations, fitted parameters, or mathematical derivations exist. The unification claim rests on participant feedback and observed benefits in the prototypes, not on any self-referential reduction or self-citation chain. The studies are independent empirical evidence rather than tautological. This is a standard, self-contained HCI contribution with no load-bearing self-definition or prediction-by-construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The contribution rests on design exploration and qualitative/quantitative user feedback rather than formal axioms, fitted parameters, or new postulated entities.

pith-pipeline@v0.9.0 · 5468 in / 1028 out tokens · 30876 ms · 2026-05-10T02:26:00.237177+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

57 extracted references · 34 canonical work pages · 6 internal anchors

  1. [1]

    Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Floren- cia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report.arXiv preprint arXiv:2303.08774 (2023)

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  2. [2]

    Glassman

    Ian Arawjo, Chelse Swoopes, Priyan Vaithilingam, Martin Wattenberg, and Elena L. Glassman. 2024. ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). Association for Computing Machinery, New York, NY, USA, Article 304, 18 ...

    work page arXiv 2024

  3. [3]

    James Betker, Gabriel Goh, Li Jing, Tim Brooks, Jianfeng Wang, Linjie Li, Long Ouyang, Juntang Zhuang, Joyce Lee, Yufei Guo, et al . 2023. Improving im- age generation with better captions.Computer Science. https://cdn. openai. com/papers/dall-e-3. pdf2, 3 (2023), 8

    2023

  4. [4]

    2007.Object-Oriented Analysis and Design with Applications (3rd ed.)

    Grady Booch, Robert Maksimchuk, Michael Engle, Bobbi Young, Jim Conallen, and Kelli Houston. 2007.Object-Oriented Analysis and Design with Applications (3rd ed.). Addison-Wesley Professional

    2007

  5. [5]

    Virginia Braun and Victoria Clarke. 2021. Thematic analysis: A practical guide. (2021)

    2021

  6. [6]

    Yuzhe Cai, Shaoguang Mao, Wenshan Wu, Zehua Wang, Yaobo Liang, Tao Ge, Chenfei Wu, Wang You, Ting Song, Yan Xia, Jonathan Tien, Nan Duan, and Furu Wei. 2024. Low-code LLM: Graphical User Interface over Large Language Models. arXiv:2304.08103 [cs.CL] https://arxiv.org/abs/2304.08103

    work page arXiv 2024

  7. [7]

    Xiang’Anthony Chen, Tiffany Knearem, and Yang Li. 2025. The GenUI Study: Exploring the Design of Generative UI Tools to Support UX Practitioners and Beyond. InProceedings of the 2025 ACM Designing Interactive Systems Conference. 1179–1196

    2025

  8. [8]

    Ian Drosos, Jack Williams, Advait Sarkar, and Nicholas Wilson. 2024. Dynamic Prompt Middleware: Contextual Prompt Refinement Controls for Comprehension Tasks. arXiv:2412.02357 [cs.HC] https://arxiv.org/abs/2412.02357

    work page arXiv 2024

  9. [9]

    Evans Xu Han, Alice Qian Zhang, Haiyi Zhu, Hong Shen, Paul Pu Liang, and Jane Hsieh. 2025. POET: Supporting Prompting Creativity and Personalization with Automated Expansion of Text-to-Image Generation. InProceedings of the 38th Annual ACM Symposium on User Interface Software and Technology. 1–18

    2025

  10. [10]

    Hilary Hutchinson, Wendy Mackay, Bo Westerlund, Benjamin B Bederson, Al- lison Druin, Catherine Plaisant, Michel Beaudouin-Lafon, Stéphane Conversy, Helen Evans, Heiko Hansen, et al. 2003. Technology probes: inspiring design for and with families. InProceedings of the SIGCHI conference on Human factors in computing systems. 17–24

    2003

  11. [11]

    Dow, and Haijun Xia

    Peiling Jiang, Jude Rayan, Steven P. Dow, and Haijun Xia. 2023. Graphologue: Exploring Large Language Model Responses with Interactive Diagrams. InPro- ceedings of the 36th Annual ACM Symposium on User Interface Software and Technology(San Francisco, CA, USA)(UIST ’23). Association for Computing Ma- chinery, New York, NY, USA, Article 3, 20 pages. doi:10....

    work page doi:10.1145/3586183.3606737 2023

  12. [12]

    Zhengbao Jiang, Frank F Xu, Jun Araki, and Graham Neubig. 2020. How can we know what language models know?Transactions of the Association for Computational Linguistics8 (2020), 423–438

    2020

  13. [13]

    Ishika Joshi, Simra Shahid, Shreeya Venneti, Manushree Vasu, Yantao Zheng, Yunyao Li, Balaji Krishnamurthy, and Gromit Yeuk-Yin Chan. 2024. CoPrompter: User-Centric Evaluation of LLM Instruction Alignment for Improved Prompt Engineering. arXiv:2411.06099 [cs.HC] https://arxiv.org/abs/2411.06099

    work page arXiv 2024

  14. [14]

    Tushar Khot, Harsh Trivedi, Matthew Finlayson, Yao Fu, Kyle Richardson, Pe- ter Clark, and Ashish Sabharwal. 2023. Decomposed Prompting: A Modu- lar Approach for Solving Complex Tasks. arXiv:2210.02406 [cs.CL] https: //arxiv.org/abs/2210.02406

    work page arXiv 2023

  15. [15]

    Soomin Kim, Jinsu Eun, Yoobin Elyson Park, Kwangwon Lee, Gyuho Lee, and Joonhwan Lee. 2025. PromptPilot: Exploring User Experience of Prompting with AI-Enhanced Initiative in LLMs.International Journal of Human–Computer Interaction(2025), 1–23. arXiv:https://doi.org/10.1080/10447318.2025.2489030 doi:10.1080/10447318.2025.2489030

    work page doi:10.1080/10447318.2025.2489030 2025

  16. [16]

    Tae Soo Kim, Yoonjoo Lee, Minsuk Chang, and Juho Kim. 2023. Cells, Gen- erators, and Lenses: Design Framework for Object-Oriented Interaction with Large Language Models. InProceedings of the 36th Annual ACM Symposium on User Interface Software and Technology(San Francisco, CA, USA)(UIST ’23). Association for Computing Machinery, New York, NY, USA, Article...

    work page doi:10.1145/3586183.3606833 2023

  17. [17]

    Tae Soo Kim, Yoonjoo Lee, Jamin Shin, Young-Ho Kim, and Juho Kim. 2024. Evallm: Interactive evaluation of large language model prompts on user-defined criteria. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–21

    2024

  18. [18]

    Jiahui Li and Roman Klinger. 2025. iPrOp: Interactive Prompt Optimization for Large Language Models with a Human in the Loop. arXiv:2412.12644 [cs.CL] https://arxiv.org/abs/2412.12644

    work page arXiv 2025

  19. [19]

    Xiaoqiang Lin, Zhongxiang Dai, Arun Verma, See-Kiong Ng, Patrick Jaillet, and Bryan Kian Hsiang Low. 2024. Prompt Optimization with Human Feedback. arXiv:2405.17346 [cs.LG] https://arxiv.org/abs/2405.17346

    work page arXiv 2024

  20. [20]

    We Need Structured Output

    Michael Xieyang Liu, Frederick Liu, Alexander J. Fiannaca, Terry Koo, Lucas Dixon, Michael Terry, and Carrie J. Cai. 2024. “We Need Structured Output”: To- wards User-centered Constraints on Large Language Model Output. InExtended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI ’24). ACM, 1–9. doi:10.1145/3613905.3650756

    work page doi:10.1145/3613905.3650756 2024

  21. [21]

    Yuhan Liu, Michael JQ Zhang, and Eunsol Choi. 2025. User feedback in human- LLM dialogues: a lens to understand users but noisy as a learning signal. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2666–2681

    2025

  22. [22]

    Huan Ma, Changqing Zhang, Yatao Bian, Lemao Liu, Zhirui Zhang, Peilin Zhao, Shu Zhang, Huazhu Fu, Qinghua Hu, and Bingzhe Wu. 2023. Fairness-guided Few-shot Prompting for Large Language Models. arXiv:2303.13217 [cs.CL] https://arxiv.org/abs/2303.13217

    work page arXiv 2023

  23. [23]

    Qianou Ma, Weirui Peng, Hua Shen, Kenneth Koedinger, and Tongshuang Wu

  24. [24]

    What you say= what you want? Teaching humans to articulate require- ments for LLMs

  25. [25]

    Qianou Ma, Weirui Peng, Chenyang Yang, Hua Shen, Ken Koedinger, and Tong- shuang Wu. 2025. What should we engineer in prompts? training humans in requirement-driven llm use.ACM Transactions on Computer-Human Interaction 32, 4 (2025), 1–27

    2025

  26. [26]

    Mackay and Anne-Laure Fayard

    Wendy E. Mackay and Anne-Laure Fayard. 1997. HCI, natural science and design: a framework for triangulation across disciplines. InProceedings of the 2nd Conference on Designing Interactive Systems: Processes, Practices, Methods, and Techniques(Amsterdam, The Netherlands)(DIS ’97). Association for Computing Machinery, New York, NY, USA, 223–234. doi:10.114...

    work page doi:10.1145/263552.263612 1997

  27. [27]

    Yuetian Mao, Junjie He, and Chunyang Chen. 2025. From Prompts to Tem- plates: A Systematic Prompt Template Analysis for Real-world LLMapps. arXiv:2504.02052 [cs.SE] https://arxiv.org/abs/2504.02052

    work page arXiv 2025

  28. [28]

    Damien Masson, Sylvain Malacria, Géry Casiez, and Daniel Vogel. 2024. Direct- gpt: A direct manipulation interface to interact with large language models. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–16

    2024

  29. [29]

    Aditi Mishra, Utkarsh Soni, Anjana Arunkumar, Jinbin Huang, Bum Chul Kwon, and Chris Bryan. 2025. PromptAid: Prompt Exploration, Perturba- tion, Testing and Iteration using Visual Analytics for Large Language Models. arXiv:2304.01964 [cs.HC] https://arxiv.org/abs/2304.01964

    work page arXiv 2025

  30. [30]

    Swaroop Mishra, Daniel Khashabi, Chitta Baral, Yejin Choi, and Hannaneh Hajishirzi. 2022. Reframing instructional prompts to gptk’s language. InFindings of the association for computational linguistics: ACL 2022. 589–612

    2022

  31. [31]

    2013.The design of everyday things: Revised and expanded edition

    Don Norman. 2013.The design of everyday things: Revised and expanded edition. Basic books

    2013

  32. [32]

    Savvas Petridis, Michael Terry, and Carrie Jun Cai. 2023. Promptinfuser: Bringing user interface mock-ups to life with large language models. InExtended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems. 1–6

    2023

  33. [33]

    Nicholas Polys, Ayat Mohammed, and Ben Sandbrook. 2024. Prompt Engineering for X3D Object Creation with LLMs. InProceedings of the 29th International ACM Conference on 3D Web Technology(Guimarães, Portugal)(Web3D ’24). Association for Computing Machinery, New York, NY, USA, Article 18, 7 pages. doi:10.1145/ 3665318.3677159

    work page arXiv 2024

  34. [34]

    Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen

  35. [35]

    Hierarchical Text-Conditional Image Generation with CLIP Latents

    Hierarchical Text-Conditional Image Generation with CLIP Latents. arXiv:2204.06125 [cs.CV] https://arxiv.org/abs/2204.06125

    work page internal anchor Pith review arXiv

  36. [36]

    Laria Reynolds and Kyle McDonell. 2021. Prompt programming for large language models: Beyond the few-shot paradigm. InExtended abstracts of the 2021 CHI conference on human factors in computing systems. 1–7

    2021

  37. [37]

    Nathalie Riche, Anna Offenwanger, Frederic Gmeiner, David Brown, Hugo Romat, Michel Pahud, Nicolai Marquardt, Kori Inkpen, and Ken Hinckley. 2025. AI- Instruments: Embodying Prompts as Instruments to Abstract & Reflect Graphical Interface Commands as General-Purpose Tools. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI...

    work page arXiv 2025

  38. [38]

    Rupak Sarkar, Bahareh Sarrafzadeh, Nirupama Chandrasekaran, Nagu Rangan, Philip Resnik, Longqi Yang, and Sujay Kumar Jauhar. 2025. Conversational user-ai intervention: A study on prompt rewriting for improved llm response generation.arXiv preprint arXiv:2503.16789(2025)

    work page arXiv 2025

  39. [39]

    The Prompt Report: A Systematic Survey of Prompt Engineering Techniques

    Sander Schulhoff, Michael Ilie, Nishant Balepur, Konstantine Kahadze, Amanda Liu, Chenglei Si, Yinheng Li, Aayush Gupta, HyoJung Han, Sevien Schul- hoff, Pranav Sandeep Dulepet, Saurav Vidyadhara, Dayeon Ki, Sweta Agrawal, Chau Pham, Gerson Kroiz, Feileen Li, Hudson Tao, Ashay Srivastava, Hevan- der Da Costa, Saloni Gupta, Megan L. Rogers, Inna Goncearenc...

    work page internal anchor Pith review arXiv 2025

  40. [40]

    L. Shen, H. Li, Y. Wang, X. Xie, and H. Qu. 2025. Prompting Generative AI with Interaction-Augmented Instructions. InExtended Abstracts of the CHI Conference on Human Factors in Computing Systems. ACM, 1–9. Xu et al

    2025

  41. [41]

    Shneiderman. 1983. Direct Manipulation: A Step Beyond Programming Lan- guages.Computer16, 8 (1983), 57–69. doi:10.1109/MC.1983.1654471

    work page doi:10.1109/mc.1983.1654471 1983

  42. [42]

    Hari Subramonyam, Roy Pea, Christopher Pondoc, Maneesh Agrawala, and Colleen Seifert. 2024. Bridging the gulf of envisioning: Cognitive challenges in prompt based interactions with llms. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–19

    2024

  43. [43]

    Sangho Suh, Meng Chen, Bryan Min, Toby Jia-Jun Li, and Haijun Xia. 2024. Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). Association for Computing Machinery, New York, NY, USA, Art...

    work page doi:10.1145/3613904.3642400 2024

  44. [44]

    Sangho Suh, Bryan Min, Srishti Palani, and Haijun Xia. 2023. Sensecape: En- abling Multilevel Exploration and Sensemaking with Large Language Models. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (UIST ’23). ACM, 1–18. doi:10.1145/3586183.3606756

    work page doi:10.1145/3586183.3606756 2023

  45. [45]

    Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, et al. 2023. Gemini: a family of highly capable multimodal models.arXiv preprint arXiv:2312.11805(2023)

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  46. [46]

    Ming Wang, Yuanzhong Liu, Xiaoyu Liang, Songlian Li, Yijie Huang, Xiaoming Zhang, Sijia Shen, Chaofeng Guan, Daling Wang, Shi Feng, Huaiwen Zhang, Yifei Zhang, Minghui Zheng, and Chi Zhang. 2024. LangGPT: Rethinking Structured Reusable Prompt Design Framework for LLMs from the Programming Language. arXiv:2402.16929 [cs.SE] https://arxiv.org/abs/2402.16929

    work page arXiv 2024

  47. [47]

    Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, and Denny Zhou. 2023. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. arXiv:2201.11903 [cs.CL] https: //arxiv.org/abs/2201.11903

    work page internal anchor Pith review arXiv 2023

  48. [48]

    Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, and Chi Wang. 2023. AutoGen: Enabling Next- Gen LLM Applications via Multi-Agent Conversation. arXiv:2308.08155 [cs.AI] https://arxiv.org/abs/2308.08155

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  49. [49]

    Tongshuang Wu, Ellen Jiang, Aaron Donsbach, Jeff Gray, Alejandra Molina, Michael Terry, and Carrie J Cai. 2022. PromptChainer: Chaining Large Language Model Prompts through Visual Programming. InExtended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems(New Orleans, LA, USA) (CHI EA ’22). Association for Computing Machinery, New Y...

    work page doi:10.1145/3491101.3519729 2022

  50. [50]

    Tongshuang Wu, Michael Terry, and Carrie Jun Cai. 2022. AI Chains: Transpar- ent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts. InProceedings of the 2022 CHI Conference on Human Factors in Comput- ing Systems(New Orleans, LA, USA)(CHI ’22). Association for Computing Ma- chinery, New York, NY, USA, Article 385, 22 pages. do...

    work page doi:10.1145/3491102.3517582 2022

  51. [51]

    Haijun Xia, Bruno Araujo, Tovi Grossman, and Daniel Wigdor. 2016. Object- Oriented Drawing. 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, 4610–4621. doi:10.1145/2858036. 2858075

    work page doi:10.1145/2858036 2016

  52. [52]

    Jinyu Xiang, Jiayi Zhang, Zhaoyang Yu, Xinbing Liang, Fengwei Teng, Jinhao Tu, Fashen Ren, Xiangru Tang, Sirui Hong, Chenglin Wu, and Yuyu Luo. 2025. Self-Supervised Prompt Optimization. arXiv:2502.06855 [cs.CL] https://arxiv. org/abs/2502.06855

    work page arXiv 2025

  53. [53]

    Xiaotong Xu, Jiayu Yin, Catherine Gu, Jenny Mar, Sydney Zhang, Jane L E, and Steven P Dow. 2024. Jamplate: Exploring llm-enhanced templates for idea reflection. InProceedings of the 29th International Conference on Intelligent User Interfaces. 907–921

    2024

  54. [54]

    Zamfirescu-Pereira, Richmond Y

    J.D. Zamfirescu-Pereira, Richmond Y. Wong, Bjoern Hartmann, and Qian Yang

  55. [55]

    Zhang, Jonathan Bragg, and Joseph Chee Chang

    Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts. InProceedings of the 2023 CHI Conference on Human Factors in Computing Systems(Hamburg, Germany)(CHI ’23). Association for Computing Machinery, New York, NY, USA, Article 437, 21 pages. doi:10.1145/3544548. 3581388

    work page doi:10.1145/3544548 2023

  56. [56]

    Lvmin Zhang, Anyi Rao, and Maneesh Agrawala. 2023. Adding conditional control to text-to-image diffusion models. InProceedings of the IEEE/CVF inter- national conference on computer vision. 3836–3847

    2023

  57. [57]

    Zhongyi Zhou, Jing Jin, Vrushank Phadnis, Xiuxiu Yuan, Jun Jiang, Xun Qian, Kristen Wright, Mark Sherwood, Jason Mayes, Jingtao Zhou, Yiyi Huang, Zheng Xu, Yinda Zhang, Johnny Lee, Alex Olwal, David Kim, Ram Iyengar, Na Li, and Ruofei Du. 2025. InstructPipe: Generating Visual Blocks Pipelines with Human Instructions and LLMs. arXiv:2312.09672 [cs.HC] doi:...

    work page doi:10.1145/3706598.3713905 2025