arXiv AI By Yuhang Huang, Chenmiao Li, Chaowei Fang

Orchestrated Reality: From Role-Play to Living, Playable Game Worlds -- LLM-Driven World Simulation as a Parameterized-Action POMDP

Read the original on arXiv AI →

arXiv:2606. 16014v1 Announce Type: cross Abstract: Many games rely on storytelling combined with systems that track levelling, NPC behaviour, and consequence simulation; bridging tightly-authored narrative with deeply-simulated worlds -- most acute in sandbox and open-world settings -- has been prohibitively expensive.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Aug 3

Shall We Play a Game? Language Models for Open-ended Wargames

arXiv:2509. 17192v3 Announce Type: replace Abstract: LLM-based social simulations can make a generated transcript look like a single behavioral signal, but the model behind that transcript may be doing several different jobs: choosing what an actor says or does, deciding what happens after an action, or both.

By Glenn Matlin, Isaac Song, Yixiong Hao, Parv Mahajan, Evan Montoya, Ryan Bard, Stuart R. Topp, Anthony Wen-Ming Zang, Mohammed Rehan Parwani, Soham Shetty, Mark Riedl
arXiv AI
Jun 16

Mind-Studio: Executable World Models with Lookahead Evaluation for Partially Observable Games

arXiv:2606. 16070v1 Announce Type: new Abstract: World-model synthesis aims to turn interaction experience into an internal model of environment dynamics.

By Yifei Dong (Hong Kong University of Science and Technology), Mingen Zheng (Hong Kong University of Science and Technology), Linquan Wu (City University of Hong Kong), Jeff Z. Pan (University of Edinburgh), Jiaxin Bai (Hong Kong Baptist University)
arXiv AI
Jul 24

DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP Servers

arXiv:2607. 20531v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed over Model Context Protocol (MCP) servers, yet the benchmarks used to evaluate them score the final answer or a fixed "ground-truth" list of tools, both of which are fragile once the underlying data is live and stateful.

By Jerzy Kami\'nski, Ilya Galyukshev, Artem Kuznetsov, Sergey Chuprin, Kirill Redko, Aidar Shumbalov, Anna Kalyuzhnaya
arXiv AI
Jul 14

MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models

arXiv:2607. 11594v1 Announce Type: new Abstract: Multi-scene navigation (clearing an objective in one bounded space and then crossing a portal into the next) is a defining feature of contemporary 3D games, but authoring it is laborious: every portal must have consistent endpoints on both sides, each interior must remain navigable once it is furnished, and the resulting connectivity must be kept consistent across many files.

By Tsz Hei Fan, Choi Wing Fung, Yuxuan Wan, Shuqing Li, Michael R. Lyu