AAAI 2026technical0 citations

Octopus: Entropy-Controlled Science Fiction Literature Generation with Persistent Memory-Context Binding

Xu Wang, Jiaju Kang, Puyu Han, Zeyu Ai, Luqi Gong

Abstract

Long-form science fiction generation demands rigorous maintenance of narrative coherence across evolving plots, character dynamics, and speculative world-building. We propose Octopus, an entropy-controlled neural framework with persistent memory-context binding that addresses these challenges through two key innovations: 1) dynamic entropy regulation balancing creativity and structural stability via narrative divergence thresholds, and 2) hierarchical memory architecture preserving character states, plot events, and scientific rules over 10K+ token spans. Evaluations across 12 sci-fi subgenres demonstrate Octopus

BibTeX
@inproceedings{aaai2026_octopusentropyco,
  title = {Octopus: Entropy-Controlled Science Fiction Literature Generation with Persistent Memory-Context Binding},
  author = {Xu Wang and Jiaju Kang and Puyu Han and Zeyu Ai and Luqi Gong},
  booktitle = {AAAI 2026},
  year = {2026}
}