Artificial Intelligence in Games

Latest papers

• Temporal-Difference Learning for Dragonchess

  Jim O'Connor, Annika Hoag, Sarah Goyette, Gary B. Parker · 2 October 2026

  Our research investigates how two adaptive AI methods, evolutionary transfer learning and TD(lambda), perform in the three-dimensional chess environment Dragonchess. The game challenges players with its unique board structure and computational load, making it an ideal setting to study how adaptive m…

• Kepler: Auditable World Models for ARC-AGI-3

  Wensen Wu · 2 October 2026

  ARC-AGI-3 evaluates agents in interactive environments whose rules and objectives must be inferred from observation. We present Kepler, an open-source harness that represents hypotheses as executable world models and validates them through retrospective transition checks and conditional prediction c…

• Benchmarking Prompt Optimization of Large Language Models With Chess

  Timoth\'ee Lesort, Alejandra L\'opez de Aberasturi G\'omez, Tristan Karch, Tom Veniat, Philippe Modard, Karl Tuyls, Ludovic Denoyer · 2 October 2026

  Evaluating large language models becomes increasingly challenging as their capabilities advance: benchmarks can saturate, public test sets risk contamination, and assessing harder tasks can require expensive grading or execution infrastructure. These challenges are amplified in automatic prompt opti…

• Game-Guided Skill Discovery through Self-Play for Playable Agent Control

  Seungeun Rho, Jeonghwan Kim, Xue Bin Peng, Sehoon Ha · 1 October 2026

  We present Game-Guided Skill Discovery (GGSD), a framework that uses self-play in games to discover motor skills that are directly playable by humans. Playable skills provide a compact abstraction for controlling embodied agents through a small set of learned behaviors rather than low-level actions.…

• A2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?

  Seonho Lee, Wonryeol Jeong, Alberto Cereser, Inha Kang, Hyeonjong Kim, Seungmin Kwak, Dongmin Park · 1 October 2026

  Delegating complete application development to coding agents requires preserving the intended design rather than simply producing plausible outputs through naive prompting. Game development provides a demanding testbed, as long-form Game Design Documents (GDDs) describe requirements that must work t…

• STRATA: Self-Learning Through Role-Aligned Tiered Agents for Real-Time Strategy Games

  Xinhe Tian, Xiaoyue Zhang, Ziyou Zhang, Jiacheng Li, Xiaoqiang Jin, Qianchuan Zhao, Gaochen Cui · 1 October 2026

  Real-time strategy (RTS) games require agents to coordinate economic development, production and construction, base defense, unit organization, and attack timing over long matches. Existing studies have applied large language models to command decision-making in RTS games, enabling agents to read te…

• Conditional Generation of Creative Chess Puzzles with Diffusion Models

  Aatu Selkee, Severi Rissanen, Xidong Feng, Tom Zahavy, Eric Malmi · 1 October 2026

  While modern language models demonstrate impressive generative capabilities, they often struggle with constrained, counter-intuitive creative tasks. To address this limitation, we explore chess puzzle generation as a rigorous testbed for computational creativity and reasoning, a domain where alterin…

• Engineering Efficient Self-Play Chess: Search, Replay, and Throughput Under Limited Compute

  Bertil Braun · 30 September 2026

  How strong can an AlphaZero-style chess system become under limited training compute when its entire learning loop is engineered for efficiency? We train from random initialization through searched self-play on a single eight-GPU node for 2.5 days. The resulting 6.32-million-parameter model reaches …

• SAGE: Structured Strategic Reasoning for Efficient LLM Game Playing

  Zhiwei Chen, Tianchun Wang, Zhongtao Rao, Haiming Zhu, Ding Cao, Tianxiang Zhao · 29 September 2026

  A strong LLM strategic agent should reason prospectively over uncertain futures, adapt its strategy to opponents' behavioral tendencies, and continuously recalibrate its decision process from interaction experience. However, incorporating these sources in free-form reasoning could lead to unsupporte…

• GlyphBench: A Playground for Language-Model Reinforcement Learning

  Roger Creus Castanyer, Marc-Alexandre C\^ot\'e, Matthew James Sargent, Augustine N. Mavor-Parker, Glen Berseth, Pablo Samuel Castro · 29 September 2026

  We introduce GlyphBench, an environment suite for reinforcement learning (RL) post-training of language-model agents, with over 360 tasks spanning diverse games. GlyphBench renders spatial observations as two-dimensional Unicode grids and connects training, evaluation, and trajectory replay through …

• SWE-Game: Can Coding Agents Build the Games We Want?

  Xiaoyu Chen, Lai Wei, Jin Wang, Xiangyu Zou, Ruochen Fan, Enze Luo, Mingzhe Yao, Jiahui Zhu, Yuhua Wen, Linghe Kong, Weiran Huang · 29 September 2026

  We introduce SWE-Game, a benchmark of 247 tasks grounded in 41 executable reference Godot games spanning 13 gameplay categories in 2D and 3D. Five task types cover development from a brief, implementation from a game design document, skeleton completion, repair of 83 injected-fault cases, and Godot-…

• Modular Discovery of General Game-Playing Algorithms with Large Language Models

  Zun Li, John Schultz, Marc Lanctot, Daniel Hennes · 29 September 2026

  General Game Playing across arbitrary games from rules alone remains challenging due to differing algorithmic requirements across game classes and strict decision-time constraints. Rather than hand-designing search heuristics for specific domains, can we leverage Large Language Models (LLMs) to disc…

• Counterfactual Self-Evolving Agents for Evidence-Grounded Reasoning

  Xing Han, Yuxin Wang, Chen Chen, Wei Dai, Gautham Krishna Gudur, Shijun Li, Hsing-Huan Chung, Gregory D. Hager, Joydeep Ghosh, Paul Pu Liang, Suchi Saria · 29 September 2026

  Self-play proposer--solver methods improve reasoning by generating tasks and learning from verified solutions. However, for evidence-identifiable tasks, where case-specific evidence and domain knowledge determine a checkable answer, self-play requires generating plausible cases whose answers can be …

• Porimon: An LLM-Based Pok\'emon Battle Agent Enhanced by Long/Short-Term Knowledge Augmented Generation

  Dongyin Zhuo, Fengjunjie Pan, Nenad Petrovic, Alois Knoll · 29 September 2026

  In this paper, we use Pok\'emon Battles as a case study to investigate how to improve the performance of LLM-based agents in tasks that require opponent-aware planning without additional fine-tuning. We propose Long/Short-Term Knowledge Augmented Generation (LSTKAG), a mechanism that enables LLM-bas…

• Witness: Discovery, Deciphering, and Epiphany in Interactive Puzzle Environments

  Guanghan Ning, Ping Liu, Linyi Li, Huangjie Zheng, Arjun Neervannan, Huu Nguyen, Michael Sklar, Deniz Zorlu, Nicolai Ouporov · 29 September 2026

  Automated science needs agents that can work out the rules of an unfamiliar environment by interacting with it. Interactive rule-discovery puzzles offer a controlled setting for studying this ability: an agent infers hidden rules through experimentation and uses what it has inferred to reach a state…

• GameBoyWorlds: A Testbed for Self-Improvement in Embodied Video Games

  Dhananjay Ashok, Adam Shen, Aslan Huo Feng, Chinmay Khanna, Jun Rui Huang, Raghav Sarmukaddam, Surendira Balaji Natarajan, Xiaotong Cui, Xincan Zhang, Thomson Yen, Hongseok Namkoong, Jonathan May, Jesse Thomason · 29 September 2026

  Powered by expert guidance, agents can operate in interactive environments; however, it is unclear whether they can learn autonomously from their own experience. To evaluate such self-improvement methods, we introduce GameBoyWorlds, a testbed for agentic self-improvement in video games. GameBoyWorld…

• Preference-based opponent shaping in differentiable games

  Xinyu Qiao, Yudong Hu, Congying Han, Weiyan Wu, Tiande Guo · 28 September 2026

  Strategy learning in game environments with multi-agent is a challenging problem. Since each agent's reward is determined by the joint strategy, a greedy learning strategy that aims to maximize its own reward may fall into a local optimum. Recent studies have proposed the opponent modeling and shapi…

• Game Arena: Strategic LLM Evaluation in Competitive Environments

  Bovard Doerschuk-Tiberi, Yao Yan, Justin Chiu, Hann Wang, Timothy Chung, Martyna Plomecka, John Schultz, Jon Lipovetz, Clayton Drazner, Yuchen Zhuang, Jaimie Hwang, Nate Keating, Riley Jones, Andrew Lee, Oran Kelly, Ian Gemp, Michael Aaron, Laurel Prince, Kate Larson, Jeff Moser, Harrison Jobe, Chad Woodford, Siqi Liu, Andrew Wang, Bo Chang, Christopher D'Mello, Diane Chaleff, Addison Howard, Johnny Yip, Chuck Sugnet, Antonio Gulli, Meghan O'Connell, Will Cukierski, Nenad Tomasev, Dima Yeroshenko, Kinjal Parekh, Roxanne Daniel, Marc Lanctot, Domino Weir, Elsa Dong, Daniel Hennes, Melissa Nalubwama, Robert Fraser, Ryan Trostle, Jun Peng, Tom Mason, Lloyd Hightower, Chiamaka Chukwuka, Yuexiang Zhai, Phoebe Kirk, Yi Su, Yuting Han, Jie Ren, Chris Prichard, Sahand Sharifzadeh, Karim Hakimzadeh, DJ Sterling, Meg Risdal, Kate Olszewska, Ya Xu, Orhan Firat, Minmin Chen · 28 September 2026

  We introduce Kaggle Game Arena, an open and ever-expanding platform to evaluate large language models (LLMs) through competitive games. Different from static benchmarks, game arena enables models to play head-to-head matchups in structured environments where the gameplay strength naturally increases…

• Self-Play Search Distillation for Large Language Model Reasoning

  Lorenzo Molfetta, Wai-Chung Kwan, Giacomo Frisoni, Luca Ragazzi, Gianluca Moro, Pavlos Vougiouklis, Jeff Z. Pan, Pasquale Minervini · 28 September 2026

  Improving reasoning abilities in Large Language Models (LLMs) requires high-quality data that exposes difficult decisions, competing alternatives, and their consequences. Data scarcity is driven by the low quality of synthetic data and the cost of human labeling. We introduce Self-Play Search Distil…

• Self-Play Pretraining with Zero Data

  Aditya Cowsik, Kfir Dolev, Michael Y. Li, G. Bruno De Luca, Nourya Cohen, Noah D. Goodman, Yoav Levine · 25 September 2026

  Advances in language modeling have been driven by scaling pretraining on ever more data. Yet, the training data is still largely curated on the model's behalf. A more general approach to pretraining would let the model learn to generate the data most useful for its own improvement. This would provid…

• PUBG Ally: A Conversational Embodied Agent as an AI Teammate

  Beomsoo Kim, Byeongju Kim, Dohyun Kim, Dongwon Kim, Eunchong Kim, Hongmin Kim, Hyeojung Im, Hyeonbin Hwang, Hyeonghwan Kim, Hyoseok Seol, Insub Im, Irene Chen, Jaeseung Jeon, Jimin Hong, Kiyoon Yoo, Minkyoung Park, Seohyeon Jung, Seungjun Chung, Sue Hyun Park, Sungwoo Kim, Youngin Cho, Yujeong Son, Kangwook Lee, Hyunseung Kim · 25 September 2026

  We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside players as a voice-enabled teammate. Building such a teammate requires combining two difficult capabilities: it must perceive and respond to a constantly changing game world under …

• Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agents

  Zheng Zhang, Liu Liu, Qi Chai, Deheng Ye, Peilin Zhao, Mao Zheng, Hao Wang · 25 September 2026

  Role-playing agents based on large language models have been widely applied in areas such as personalized assistance and social simulation. Recent RL methods typically train on a fixed scenario pool collected before learning begins. This creates a distributional bottleneck: as the agent improves, th…

• Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms

  Xinjie Shen, Wei Fan, Xudong Guo, Jianhong Tu, Yang Su, Chuqiao Kuang, Yinger Zhang, Dayiheng Liu · 24 September 2026

  Language-model agents increasingly face long-horizon tasks with evolving state, interdependent decisions, and delayed outcomes. Scaling their training requires diverse agentic environments, dependable outcome signals, and low extension cost. Existing generation pipelines commonly construct an enviro…

• OpenBlock: Constructive and Verified Content Generation for Adaptive Tile-Matching Games

  Jiang Jun · 22 September 2026

  Tile-matching puzzle games serve hundreds of millions of players, yet the content-generation algorithms that decide which pieces to present at each turn remain proprietary, and no open platform exists for studying adaptive difficulty in this genre. We present an adaptive tile-matching platform whose…

• GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay

  Yiran Wang, Xingyilang Yin, Junfu Pu, Guangzhi Wang, Kaifeng Li, Mingyu Ouyang, Huiqiang Sun, Lingen Li, Cheng Cheng, Wangbo Yu, Honghao Chen, Xiaodong Cun, Chi-Man Pun, Zhiguo Cao, Ying Shan · 22 September 2026

  Modern video games provide a measurable testbed for AI models, combining abilities of visual understanding, instruction decomposition, goal planning, and precise action control over multiple temporal horizons. Existing datasets and benchmarks, however, either cover a narrow range of games, lack lang…