Cognitive BASIC: An In-Model Interpreted Reasoning Language for LLMs

TL;DR

Cognitive BASIC introduces a simple, interpretable programming language within LLMs that structures reasoning into explicit steps, enhancing transparency and interpretability of complex reasoning processes.

Contribution

It proposes a minimal, BASIC-style in-model interpreter that enables explicit, stepwise reasoning and knowledge extraction within large language models.

Findings

All tested LLMs can execute Cognitive BASIC programs.

Models show strong performance on reasoning and knowledge tasks.

The approach improves transparency and conflict detection in LLM reasoning.

Abstract

Cognitive BASIC is a minimal, BASIC-style prompting language and in-model interpreter that structures large language model (LLM) reasoning into explicit, stepwise execution traces. Inspired by the simplicity of retro BASIC, we repurpose numbered lines and simple commands as an interpretable cognitive control layer. Modern LLMs can reliably simulate such short programs, enabling transparent multi-step reasoning inside the model. A natural-language interpreter file specifies command semantics, memory updates, and logging behavior. Our mental-model interpreter extracts declarative and procedural knowledge, detects contradictions, and produces resolutions when necessary. A comparison across three LLMs on a benchmark of knowledge extraction, conflict detection, and reasoning tasks shows that all models can execute Cognitive BASIC programs, with overall strong but not uniform performance.