EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World

2026-07-19

AI Summary

Existing interactive literary simulations are often limited to static character imitation or isolated scene generation, failing to capture the co-evolution of characters and their world over time. This work proposes an open-ended architectural framework that models literary simulation as a long-term co-evolutionary system. By coupling Character Agents with an LLM-based World Model, the framework enables continuous interaction and mutual updating between character states and world dynamics. Additionally, a trajectory-level LLM-as-Judge multidimensional evaluation protocol is introduced. Evaluated on a dataset spanning 57 books and 138,596 samples, the approach demonstrates significant improvements in coherence and persistence of both character behavior and world development in long-horizon simulations.

Abstract

This paper introduces EvolvingWorld, a framework and benchmark for character and world co-evolution in interactive literary worlds. Existing systems either treat interactive literary simulation as static persona imitation or isolated scene generation, failing to capture how characters and worlds evolve together over time. To address this, EvolvingWorld models literary simulation as a long-horizon process where characters interact, scenes progress, and character and world states are persistently updated. Unlike prior systems relying on fixed schemas, EvolvingWorld adopts an open-schema framework to support simulation across diverse literary worlds. The framework consists of 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, we formulate 7 trainable tasks for scene initialization, interaction generation, and state update. We construct a dataset from 57 books, producing 138,596 supervised training samples and 222 snapshots for testing. Furthermore, we introduce a trajectory-level LLM-as-Judge evaluation protocol spanning 10 dimensions and 20 metrics. Experiments show that EvolvingWorld can improve long-horizon simulation by effectively maintaining persistent, coherent character and world development.

Problem

• interactive literary world
• character-world co-evolution
• long-horizon simulation
• persistent state
• open-schema framework

Innovation

• open-schema
• co-evolution
• interactive literary simulation
• persistent state update
• LLM-based world model