The paper introduces Forking Garden, a branching game generation system that threads narrative archetype as a persistent semantic signal throughout the generation pipeline. Narrative progression is modeled with soft Rise/Fall states, guiding the creation of plot nodes, structural constraints, encounter composition, objectives, rewards, and difficulty adaptation. Experiments across ten storylines show that the system produces distinct archetypal trajectories, improves entity diversity, and that Rise/Fall distinctions remain meaningful during play, aiding both narrative understanding and creator interpretation.
By Yunge Wen, Chenliang Huang, Hangyu Zhou, Zhuo Zeng, Yuxuan Weng, Timothy Merino, Julian Togelius, Max Kreminski, Sam Earle
arXiv:2609.25652v1 Announce Type: new
Abstract: Recent game world models support realistic visual simulation and interactive gameplay based on player inputs. However, they typically learn environment...
By Zijun Lin, Zhiyang Deng, Yuzhe Wu, Bihan Wen, Yeying Jin
arXiv:2608. 04037v1 Announce Type: cross Abstract: Designing narrative-grounded interactive experiences remains labor-intensive because interactive content must align with the underlying world implied by the narrative.
By Yi-Chun Chen
arXiv:2407. 09013v2 Announce Type: replace Abstract: The attempt to utilize machine learning in PCG has been made in the past.
By Xinyu Mao, Wanli Yu, Kazunori D Yamada, Michael R. Zielewski
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
OpenBlock is an open, adaptive tile‑matching platform that uses a dual‑track content‑generation system: a deterministic rule‑based generator and an optional learned generator, both verified to ensure every piece set is fully placeable. A self‑play reinforcement‑learning agent diagnoses that long‑bar pieces become largely unplaceable at high board fill, indicating board‑state degeneration rather than difficulty drives late‑game failure. In live play, the learned track improves day‑1 retention by 1.8 percentage points and session duration by 7% compared to the rule track alone.
By Jiang Jun
The paper introduces the Abstraction Agent, a zero‑shot pipeline that employs a large language model to automatically generate continuous strategic features from a natural‑language game description, score private states, and cluster them into abstraction buckets without any game‑specific evaluators or training data. The pipeline consists of four phases—feature discovery with calibration anchors, batched private‑state scoring, correlation‑based feature selection, and k‑means clustering—and achieves significant reductions in lifted‑strategy exploitability in heads‑up no‑limit Texas hold’em and outperforms scalar rank baselines in ROVER Trials. The method also transfers to other games such as four‑card Pot‑Limit Omaha, HUNL preflop and flop, and Riichi Mahjong, demonstrating that it can uncover strategic concepts that align with recognized game theory insights.
By Boning Li, Longbo Huang
The paper introduces a method for creating reactive character behaviors in continuous games as compact, human‑readable programs. It searches over a domain‑specific language that uses reactive geometric decisions and higher‑order constructs to discretize continuous behavior space, while eliminating redundant program forms through synthesis antipatterns. The approach, called agentic sketching, combines bottom‑up symbolic enumeration with top‑down guidance from a coding agent, and outperforms either technique alone on a benchmark of 14 continuous games.
By Maxim Gumin, Hsueh-Ti Derek Liu, Victor Zordan, Daniel Ritchie
arXiv:2605.13570v2 Announce Type: replace
Abstract: Constraint-based game content generators that learn local constraints from existing content, such as Wave Function Collapse (WFC), can generate vis...
By Debosmita Bhaumik, Julian Togelius, Georgios N. Yannakakis, Ahmed Khalifa
arXiv:2607. 21195v1 Announce Type: cross Abstract: Chess is a two player strategic game that is embedded in classical AI culture as it was once the frontier for intelligent behaviour.
By Nicos Angelopoulos (University College,Imperial College, London UK), Jan Wielemaker (SWI-Prolog solutions)
arXiv:2608.21833v1 Announce Type: new
Abstract: Recent large language models (LLMs) can operate as coding agents that build complete games from natural language requests. Game development is especial...
By Kun Chen, Haorong Hong, Peizhong Gao, Jianfeng Lin, Tongxu Luo, Yuxuan Xie, Chenxu Liu, Jieling He, Zhongyuan Liu, Zeno Zeng
The paper introduces Code World Model, a framework that decouples world evolution from visual rendering by using a coding agent as a world brain. The agent reasons about events, generates executable code to maintain persistent state, and a proxy representation links this state to a video model for high‑fidelity visual output. Experiments with MiniMax‑H3 show that the system can follow proxy‑based spatiotemporal specifications while preserving rich visual dynamics, illustrating a new approach to open‑ended world modeling.
By Yiwen Chen, Guosheng Lin, Chi Zhang