ChatLogo: A Large Language Model-Driven Hybrid Natural-Programming Language Interface for Agent-based Modeling and Programming
This work addresses the problem of making computational and complex systems thinking more accessible for novice learners, though it appears incremental as it builds on existing efforts in scaffolding learning and leveraging LLMs.
The authors tackled the challenge of supporting open-ended constructionist learning of agent-based modeling and programming by proposing ChatLogo, a hybrid natural-programming language interface driven by large language models, which aims to provide a more user-friendly interface for novice learners and reduce over-reliance on any single LLM.
Building on Papert (1980)'s idea of children talking to computers, we propose ChatLogo, a hybrid natural-programming language interface for agent-based modeling and programming. We build upon previous efforts to scaffold ABM & P learning and recent development in leveraging large language models (LLMs) to support the learning of computational programming. ChatLogo aims to support conversations with computers in a mix of natural and programming languages, provide a more user-friendly interface for novice learners, and keep the technical system from over-reliance on any single LLM. We introduced the main elements of our design: an intelligent command center, and a conversational interface to support creative expression. We discussed the presentation format and future work. Responding to the challenges of supporting open-ended constructionist learning of ABM & P and leveraging LLMs for educational purposes, we contribute to the field by proposing the first constructionist LLM-driven interface to support computational and complex systems thinking.