Paper 2607.17250
EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World
- Published
- Jul 2026
- Research lab
- Independent
- Citations
- 0
- GitHub
- 18 stars
01 In brief
Summary
EvolvingWorld is a framework and benchmark for simulating interactive literary worlds where characters and the world co-evolve over long horizons.
It addresses limitations of existing systems that treat role-play as static persona imitation or isolated scene generation.
The framework uses an open-schema design, coupling a Character Agent for multi-character role-play and persistent profile evolution with an LLM-based World Model for global and location/entity-level state maintenance and scene progression.
It decomposes simulation into 7 trainable tasks: scene_cast, location_scenario, motivation_update, next_character, interaction_gen, world_update, and character_update.
A dataset was constructed from 57 books, yielding 138,596 supervised training samples and 222 test snapshots.
A trajectory-level LLM-as-Judge evaluation protocol spans 10 dimensions and 20 metrics.
Experiments show that EvolvingWorld reduces long-horizon performance degradation compared to prior frameworks like BookWorld, improving character consistency, evolution quality, and world state maintenance.
The framework supports open-schema character and world states, allowing for diverse literary worlds and persistent development beyond initial descriptions.
02 From the paper
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.