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

• URL: http://arxiv.org/abs/2607.17250v1
• Date: Sun, 19 Jul 2026 13:40:34 GMT
• Title: EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World
• Abstract summary: EvolvingWorld is a framework and benchmark for character and world co-evolution in interactive literary worlds.<n>We construct a dataset from 57 books, producing 138,596 supervised training samples and 222 snapshots for testing.
• Score: 60.96623714739525
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States [106.40454498751295]
  Puffin-World integrates physical understanding, spatial simulation, and 3D world generation and reconstruction without relying on external offline modules.<n>Our framework jointly models three native world states: physics (gravity field and latitude), geometry (depth), and appearance (image)<n>By grounding absolute camera properties in the real world, Puffin-World enables physically consistent and visually stable world generation.
  arXiv  Detail & Related papers  (2026-09-03T17:59:13Z)
• Code World Model: Coding Agent as World Brain [51.31807545747191]
  We introduce Code World Model, a framework that separates world evolution from visual realization.<n>A coding agent serves as the world brain, reasoning about events and their consequences.<n>To connect executable state with visual generation, we introduce a proxy representation that encodes frame-wisetemporal constraints into a proxy video.
  arXiv  Detail & Related papers  (2026-08-26T15:37:33Z)
• Bridging the Agent-World Gap: Text World Models for LLM-based Agents [83.8237017249529]
  Large language model (LLM)-based agents are increasingly used in interactive textual environments.<n>Many remain largely reactive, mapping observations to actions without an explicit model of how these environments are structured and evolve.<n>This motivates text world models (TWMs): transition models over textual states that, given a state and a candidate action, predict the resulting webpage, terminal output, API response, or user reply.<n>We systematically review text world models for LLM-based agents, organized around a formal framework and the agent lifecycle.
  arXiv  Detail & Related papers  (2026-06-08T04:58:52Z)
• AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization [79.26935895370191]
  AnchorWorld is a framework that advances egocentric simulation through enhanced interaction integrity.<n> auxiliary training supervision incorporates viewpoints decoupled from the agent's first-person sensorium.<n>We propose a simple yet effective mechanism for customizing self-evolving worlds.
  arXiv  Detail & Related papers  (2026-06-05T14:43:13Z)
• Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond [209.35045331678043]
  We introduce a "levels x laws" taxonomy organized along two axes.<n>The first defines three capability levels: L1 Predictor, which learns one-step local transition operators; L2 Simulator, which composes them into multi-step, action-conditioned rollouts that respect domain laws; and L3 Evolver, which autonomously revises its own model when predictions fail against new evidence.<n>We synthesize over 400 works and summarize more than 100 representative systems spanning model-based reinforcement learning, video generation, web and GUI agents, multi-agent social simulation, and AI-driven scientific discovery.
  arXiv  Detail & Related papers  (2026-04-24T17:48:47Z)
• Interactive World Simulator for Robot Policy Training and Evaluation [21.481187472784047]
  We present Interactive World Simulator, a framework for building interactive world models from a robot interaction dataset.<n>In our experiments, the learned world models produce interaction-consistent pixel-level predictions.<n>We find that policies trained on world-model-generated data perform comparably to those trained on the same amount of real-world data.
  arXiv  Detail & Related papers  (2026-03-09T16:13:32Z)
• LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models [32.92934803081681]
  Recent generative video world models aim to simulate visual environment evolution, allowing an observer to interactively explore the scene via camera control.<n>They implicitly assume that the world only evolves within the observer's field of view.<n>Once an object leaves the observer's view, its state is "frozen" in memory, and revisiting the same region later often fails to reflect events that should have occurred in the meantime.<n>We propose LiveWorld, a novel framework that extends video world models to support persistent world evolution.
  arXiv  Detail & Related papers  (2026-03-07T10:31:39Z)
• MetaWorld: Skill Transfer and Composition in a Hierarchical World Model for Grounding High-Level Instructions [2.6994954303270564]
  We propose MetaWorld, a hierarchical world model that integrates semantic planning and physical control.<n>We show it outperforms world model-based RL in task completion and motion coherence.
  arXiv  Detail & Related papers  (2026-01-24T16:11:45Z)
• WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World [100.68103378427567]
  Generative world models are reshaping embodied AI, enabling agents to synthesize realistic 4D driving environments that look convincing but often fail physically or behaviorally.<n>We introduce WorldLens, a full-spectrum benchmark evaluating how well a model builds, understands, and behaves within its generated world.<n>We further construct WorldLens-26K, a large-scale dataset of human-annotated videos with numerical scores and textual rationales, and develop WorldLens-Agent.
  arXiv  Detail & Related papers  (2025-12-11T18:59:58Z)
• CoEx -- Co-evolving World-model and Exploration [24.960276990968822]
  Planning in modern LLM agents relies on the utilization of LLM as an internal world model.<n>Existing agent designs fail to effectively assimilate new observations into dynamic updates of the world model.<n>We introduce a hierarchical agent architecture, CoEx, in which hierarchical state abstraction allows LLM planning to co-evolve with a dynamically updated model of the world.
  arXiv  Detail & Related papers  (2025-07-29T23:13:09Z)
• BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation [60.53187087043975]
  BookWorld is a system for constructing and simulating book-based multi-agent societies.<n>BookWorld enables diverse applications including story generation, interactive games and social simulation.
  arXiv  Detail & Related papers  (2025-04-20T08:56:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.