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

TL;DR

SimStep introduces a chain-of-abstractions framework that enhances control, traceability, and refinement in AI-assisted simulation creation, especially for educators, by decomposing the process into meaningful checkpoints.

Contribution

The paper presents the CoA framework and its implementation in SimStep, enabling incremental specification, debugging, and interpretability in natural language-driven simulation authoring.

Findings

Educators found SimStep increased control and understanding.

SimStep effectively identified and corrected model assumptions.

The approach improved the interpretability of AI-generated 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.