ReactiveGWM: Steering NPC in Reactive Game World Models

• URL: http://arxiv.org/abs/2605.15256v1
• Date: Thu, 14 May 2026 17:52:03 GMT
• Title: ReactiveGWM: Steering NPC in Reactive Game World Models
• Abstract summary: We introduce ReactiveGWM, a reactive game world model that synthesizes dynamic interactions between the player and NPC.<n>Our learned modules can be plugged directly into off-the-shelf, unannotated world models of different games.<n>This enables zero-shot strategy transfer: our learned modules can be plugged directly into off-the-shelf, unannotated world models of different games.
• Score: 37.35401641615055
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current game world models simulate environments from a subjective, player-centric perspective. However, by treating the Non-Player Character (NPC) merely as background pixels, these models cannot capture interactions between the player and NPC. In that sense, they act as passive video renderers rather than real simulation engines, lacking the physical understanding needed to model action-induced NPC reactivities. We introduce ReactiveGWM, a reactive game world model that synthesizes dynamic interactions between the player and NPC. Instead of entangling all interaction dynamics, ReactiveGWM explicitly decouples player controls from NPC behaviors. Player actions are injected into the diffusion backbone via a lightweight additive bias, while high-level NPC responses (e.g., Offense, Control, Defense) are grounded through cross-attention modules. Crucially, these modules learn a game-agnostic representation of interactive logic. This enables zero-shot strategy transfer: our learned modules can be plugged directly into off-the-shelf, unannotated world models of different games. This instantly unlocks steerable NPC interactions without any domain-specific retraining. Evaluated on two Street Fighter games, ReactiveGWM maintains fine-grain player controllability while achieving robust, prompt-aligned NPC strategy adherence, paving the way for scalable, strategy-rich interaction with the NPC.

Related papers

• GameWAM: A World Action Model for Video Games [36.43342575951464]
  We introduce GameWAM, to our knowledge the first WAM for native closed-loop gameplay and GUI control.<n>To support joint world-action learning, we construct synchronized gameplay and GUI trajectories.<n>Experiments demonstrate competitive task success with fewer executed native actions than the compared agents.
  arXiv  Detail & Related papers  (2026-08-25T17:21:15Z)
• WorldMind: Decoupled Game World Model for State-Aware NPC Behavior [9.251161502042368]
  Non-player character (NPC) behavior is either implicitly entangled with video generation or explicitly prescribed through external control signals.<n>We introduce WorldMind, to our knowledge the first decoupled framework for state-aware NPC behavior in game world models.<n>By reconnecting layers in a closed interaction loop, WorldMind grounds NPC behavior in the evolving game state.
  arXiv  Detail & Related papers  (2026-08-18T04:09:17Z)
• Infinite Worlds with Versatile Interactions [72.56254206708059]
  LingBot-World 2.0 (also known as LingBot-World-Infinity) is an advanced iteration of LingBot-World.<n>This update introduces highly diverse interactive elements, comprising a broader spectrum of actions.<n>To facilitate a shared experience, we develop an interface that permits multiple players to simultaneously immerse themselves in this vivid world simulator.
  arXiv  Detail & Related papers  (2026-07-08T15:33:25Z)
• Multiplayer Interactive World Models with Representation Autoencoders [28.451678067070777]
  We introduce the first multiplayer world model for highly dynamic environments governed by complex physical interactions.<n>We study this problem in the game of Rocket League, where players compete and cooperate under fast, tightly coupled dynamics.
  arXiv  Detail & Related papers  (2026-07-06T17:31:52Z)
• ActionParty: Multi-Subject Action Binding in Generative Video Games [117.52562594944679]
  ActionParty is a controllable multi-subject world model for generative video games.<n>We demonstrate the first video world model capable of controlling up to seven players simultaneously across 46 diverse environments.
  arXiv  Detail & Related papers  (2026-04-02T17:59:58Z)
• MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines [55.641812280108574]
  We introduce an explicit external memory into the system that is continually updated by user actions and queried throughout the generation roll-out.<n>This design gives users direct, editable control over environment structure via an editable memory representation.<n>It naturally extends to real-time multiplayer rollouts with coherent viewpoints and consistent cross-player interactions.
  arXiv  Detail & Related papers  (2026-03-03T18:58:17Z)
• Learning Controllable and Diverse Player Behaviors in Multi-Agent Environments [0.0]
  This paper introduces a reinforcement learning framework that enables controllable and diverse player behaviors without relying on human gameplay data.<n>We define player behavior in an N-dimensional continuous space and uniformly sample target behavior vectors from a region that encompasses a subset representing real human styles.<n>A single PPO-based multi-agent policy can reproduce new or unseen play styles without retraining.
  arXiv  Detail & Related papers  (2025-12-11T17:26:24Z)
• Collaborative Quest Completion with LLM-driven Non-Player Characters in Minecraft [14.877848057734463]
  We design a minigame within Minecraft where a player works with two GPT4-driven NPCs to complete a quest. On analyzing the game logs and recordings, we find that several patterns of collaborative behavior emerge from the NPCs and the human players. We believe that this preliminary study and analysis will inform future game developers on how to better exploit these rapidly improving generative AI models for collaborative roles in games.
  arXiv  Detail & Related papers  (2024-07-03T19:11:21Z)
• Towards a Holodeck-style Simulation Game [40.044978986425676]
  Infinitia uses generative image and language models to reshape all aspects of the setting and NPCs based on a short description from the player. Infinitia is implemented in the Unity engine with a server-client architecture. It uses a multiplayer framework to allow humans to be present and interact in the simulation.
  arXiv  Detail & Related papers  (2023-08-22T19:19:19Z)
• Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion Models [68.85478477006178]
  We present a Promptable Game Model (PGM) for neural video game simulators. It allows a user to play the game by prompting it with high- and low-level action sequences. Most captivatingly, our PGM unlocks the director's mode, where the game is played by specifying goals for the agents in the form of a prompt. Our method significantly outperforms existing neural video game simulators in terms of rendering quality and unlocks applications beyond the capabilities of the current state of the art.
  arXiv  Detail & Related papers  (2023-03-23T17:43:17Z)
• Learning to Simulate Dynamic Environments with GameGAN [109.25308647431952]
  In this paper, we aim to learn a simulator by simply watching an agent interact with an environment. We introduce GameGAN, a generative model that learns to visually imitate a desired game by ingesting screenplay and keyboard actions during training.
  arXiv  Detail & Related papers  (2020-05-25T14:10:17Z)

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.