Reproduce “Towards Self-Evolving Narrative Systems: Real-Time Adaptation and Long-Term Optimization with LLMs” 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

Ruisheng Sun, Jiaqi Shao, Weijia Han, Linxi Ju, Yunzhen Zhang, Binyan Sun, Rong Chen, Benjamin Blas Maristany and 4 more

The authors present a system combining an authored story backbone with language-model adaptation and prompt revisions between playthroughs, guided by player feedback. In a 12-person study of one nine-scene Fort Joy arc, optimization raised coherence ratings from 3.9 to 4.2, NPC consistency from 4.3 to 4.6, and agency from 3.3 to 3.5 (p < .1). Findings are limited to this case study.

Summary by alphaXiv.

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