Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

EvolvingWorld: Open-Schema Framework for Co-Evolving Characters and Worlds in Literary Simulation

AI By Crimson AI Hugging Face Papers 21 July 2026 · 00:00 15 views
Share: X Telegram

Hugging Face researchers introduce EvolvingWorld, a framework and benchmark for long-horizon literary world simulation where characters and world states co-evolve through ongoing interactions, using an open-schema approach across 57 books.

EvolvingWorld: Open-Schema Framework for Co-Evolving Characters and Worlds in Literary Simulation

Key points

Hugging Face researchers have unveiled EvolvingWorld, a novel framework and benchmark designed to model the co-evolution of characters and worlds in interactive literary simulations. Unlike prior systems that treat literary simulation as static persona imitation or isolated scene generation, EvolvingWorld captures how characters and worlds evolve together over time through a long-horizon process.

The framework adopts an open-schema approach, enabling support for diverse literary worlds without relying on fixed schemas. It comprises two coupled modules: a Character Agent for multi-character role-play and persistent profile evolution, and an LLM-based World Model for global and location/entity-level state maintenance and scene progression.

Based on this architecture, the researchers formulated 7 trainable tasks covering scene initialization, interaction generation, and state update. A dataset was constructed from 57 books, yielding 138,596 supervised training samples and 222 snapshots for testing. Additionally, a trajectory-level LLM-as-Judge evaluation protocol was introduced, spanning 10 dimensions and 20 metrics.

Experiments demonstrate that EvolvingWorld improves long-horizon simulation by effectively maintaining persistent, coherent character and world development. The work addresses a key gap in interactive literary simulation, moving beyond static persona imitation to dynamic co-evolution.

Dataset StatisticValue
Number of books57
Supervised training samples138,596
Test snapshots222
Trainable tasks7
Evaluation dimensions10
Evaluation metrics20
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1