SimStep: Chain-of-Abstractions for Incremental Specification and Debugging of AI-Generated Interactive Simulations

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kaputa, Zoe, Rajaram, Anika, Feliciano, Vryan Almanon, Lyu, Zhuoyue, Agrawala, Maneesh, Subramonyam, Hari
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912479569772544
author Kaputa, Zoe
Rajaram, Anika
Feliciano, Vryan Almanon
Lyu, Zhuoyue
Agrawala, Maneesh
Subramonyam, Hari
author_facet Kaputa, Zoe
Rajaram, Anika
Feliciano, Vryan Almanon
Lyu, Zhuoyue
Agrawala, Maneesh
Subramonyam, Hari
contents Programming-by-prompting with generative AI offers a new paradigm for end-user programming, shifting the focus from syntactic fluency to semantic intent. This shift holds particular promise for non-programmers such as educators, who can describe instructional goals in natural language to generate interactive learning content. Yet in bypassing direct code authoring, many of programming's core affordances - such as traceability, stepwise refinement, and behavioral testing - are lost. We propose the Chain-of-Abstractions (CoA) framework as a way to recover these affordances while preserving the expressive flexibility of natural language. CoA decomposes the synthesis process into a sequence of cognitively meaningful, task-aligned representations that function as checkpoints for specification, inspection, and refinement. We instantiate this approach in SimStep, an authoring environment for teachers that scaffolds simulation creation through four intermediate abstractions: Concept Graph, Scenario Graph, Learning Goal Graph, and UI Interaction Graph. To address ambiguities and misalignments, SimStep includes an inverse correction process that surfaces in-filled model assumptions and enables targeted revision without requiring users to manipulate code. Evaluations with educators show that CoA enables greater authoring control and interpretability in programming-by-prompting workflows.
format Preprint
id arxiv_https___arxiv_org_abs_2507_09664
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SimStep: Chain-of-Abstractions for Incremental Specification and Debugging of AI-Generated Interactive Simulations
Kaputa, Zoe
Rajaram, Anika
Feliciano, Vryan Almanon
Lyu, Zhuoyue
Agrawala, Maneesh
Subramonyam, Hari
Human-Computer Interaction
Artificial Intelligence
Programming-by-prompting with generative AI offers a new paradigm for end-user programming, shifting the focus from syntactic fluency to semantic intent. This shift holds particular promise for non-programmers such as educators, who can describe instructional goals in natural language to generate interactive learning content. Yet in bypassing direct code authoring, many of programming's core affordances - such as traceability, stepwise refinement, and behavioral testing - are lost. We propose the Chain-of-Abstractions (CoA) framework as a way to recover these affordances while preserving the expressive flexibility of natural language. CoA decomposes the synthesis process into a sequence of cognitively meaningful, task-aligned representations that function as checkpoints for specification, inspection, and refinement. We instantiate this approach in SimStep, an authoring environment for teachers that scaffolds simulation creation through four intermediate abstractions: Concept Graph, Scenario Graph, Learning Goal Graph, and UI Interaction Graph. To address ambiguities and misalignments, SimStep includes an inverse correction process that surfaces in-filled model assumptions and enables targeted revision without requiring users to manipulate code. Evaluations with educators show that CoA enables greater authoring control and interpretability in programming-by-prompting workflows.
title SimStep: Chain-of-Abstractions for Incremental Specification and Debugging of AI-Generated Interactive Simulations
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2507.09664