{"ID":2895246,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.09664","arxiv_id":"2507.09664","title":"SimStep: Chain-of-Abstractions for Incremental Specification and Debugging of AI-Generated Interactive Simulations","abstract":"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.","short_abstract":"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 c...","url_abs":"https://arxiv.org/abs/2507.09664","url_pdf":"https://arxiv.org/pdf/2507.09664v1","authors":"[\"Zoe Kaputa\",\"Anika Rajaram\",\"Vryan Almanon Feliciano\",\"Zhuoyue Lyu\",\"Maneesh Agrawala\",\"Hari Subramonyam\"]","published":"2025-07-13T14:54:17Z","proceeding":"cs.HC","tasks":"[\"cs.HC\",\"cs.AI\"]","methods":"[]","has_code":false}