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

2025-07-13

AI Summary

This study addresses the challenge of reconciling natural language flexibility with core programming competencies—traceability, incremental development, and behavioral verification—in generative AI programming for non-programmers, particularly educators. Method: We propose the first chain-of-abstraction framework, defining four intermediate representations—concepts, scenarios, learning objectives, and interface interactions—to enable stepwise mapping from natural language intent to pedagogical simulation systems, augmented by bidirectional refinement. Integrating prompt engineering, NLP, and visual modeling, we construct a multi-layered abstract graph structure supporting closed-loop feedback. Contribution/Results: User evaluation demonstrates that our approach significantly enhances educators’ controllability over and conceptual understanding of AI-generated artifacts, enabling incremental, iterative construction and optimization of executable teaching simulations—from ambiguous natural language descriptions to validated, runnable systems.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

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.

Problem

• Enables non-programmers to create interactive simulations via natural language
• Recovers programming affordances lost in AI-generated content creation
• Provides incremental specification and debugging for AI-generated simulations

Innovation

• Chain-of-Abstractions framework for stepwise refinement
• Four intermediate graphs for simulation creation
• Inverse correction process for targeted revision