Reproduce “Human-LLM Cognitive Extension: A Framework for Studying Coupled Cognition” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Ernesto Biempica, Emiliano Bruner, Juan F Poyatos

The authors introduce the Human-LLM Cognitive Extension (HLCE) framework to clarify what human–AI cognition studies measure and what their findings support. It distinguishes human, AI, combined, and post-assistance outcomes, and treats interaction architecture as part of the experiment. A synthetic troubleshooting example shows different routes to the same answer, not evidence of improved cognition or transparency effects.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.