Paper
Resource-constrained Amazons chess decision framework integrating large language models and graph attention
Authors
Tianhao Qian, Zhuoxuan Li, Jinde Cao, Xinli Shi, Hanjie Liu, Leszek Rutkowski
Abstract
Artificial intelligence has advanced significantly through the development of intelligent game-playing systems, providing rigorous testbeds for decision-making, strategic planning, and adaptive learning. However, resource-constrained environments pose critical challenges, as conventional deep learning methods heavily rely on extensive datasets and computational resources. In this paper, we propose a lightweight hybrid framework for the Game of the Amazons, which explores the paradigm of weak-to-strong generalization by integrating the structural reasoning of graph-based learning with the generative capabilities of large language models. Specifically, we leverage a Graph Attention Autoencoder to inform a multi-step Monte Carlo Tree Search, utilize a Stochastic Graph Genetic Algorithm to optimize evaluation signals, and harness GPT-4o-mini to generate synthetic training data. Unlike traditional approaches that rely on expert demonstrations, our framework learns from noisy and imperfect supervision. We demonstrate that the Graph Attention mechanism effectively functions as a structural filter, denoising the LLM's outputs. Experiments on a 10$\times$10 Amazons board show that our hybrid approach not only achieves a 15\%--56\% improvement in decision accuracy over baselines but also significantly outperforms its teacher model (GPT-4o-mini), achieving a competitive win rate of 45.0\% at N=30 nodes and a decisive 66.5\% at only N=50 nodes. These results verify the feasibility of evolving specialized, high-performance game AI from general-purpose foundation models under stringent computational constraints.
Metadata
Related papers
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jian... • 2026-03-30
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or • 2026-03-30
Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books
Minh-Thu Do, Quynh-Chau Le-Tran, Duc-Duy Nguyen-Mai, Thien-Trang Nguyen, Khan... • 2026-03-30
ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Anuj Diwan, Eunsol Choi, David Harwath • 2026-03-30
RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems
Oliver Aleksander Larsen, Mahyar T. Moghaddam • 2026-03-30
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.10512v1</id>\n <title>Resource-constrained Amazons chess decision framework integrating large language models and graph attention</title>\n <updated>2026-03-11T08:07:55Z</updated>\n <link href='https://arxiv.org/abs/2603.10512v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.10512v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Artificial intelligence has advanced significantly through the development of intelligent game-playing systems, providing rigorous testbeds for decision-making, strategic planning, and adaptive learning. However, resource-constrained environments pose critical challenges, as conventional deep learning methods heavily rely on extensive datasets and computational resources. In this paper, we propose a lightweight hybrid framework for the Game of the Amazons, which explores the paradigm of weak-to-strong generalization by integrating the structural reasoning of graph-based learning with the generative capabilities of large language models. Specifically, we leverage a Graph Attention Autoencoder to inform a multi-step Monte Carlo Tree Search, utilize a Stochastic Graph Genetic Algorithm to optimize evaluation signals, and harness GPT-4o-mini to generate synthetic training data. Unlike traditional approaches that rely on expert demonstrations, our framework learns from noisy and imperfect supervision. We demonstrate that the Graph Attention mechanism effectively functions as a structural filter, denoising the LLM's outputs. Experiments on a 10$\\times$10 Amazons board show that our hybrid approach not only achieves a 15\\%--56\\% improvement in decision accuracy over baselines but also significantly outperforms its teacher model (GPT-4o-mini), achieving a competitive win rate of 45.0\\% at N=30 nodes and a decisive 66.5\\% at only N=50 nodes. These results verify the feasibility of evolving specialized, high-performance game AI from general-purpose foundation models under stringent computational constraints.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.NE'/>\n <published>2026-03-11T08:07:55Z</published>\n <arxiv:comment>20 pages, 15 figures. Supported by the National Key Research and Development Project of China (No. 2020YFA0714300), NSFC (No. 61833005, 12061088), the Open Project of Key Laboratory of Transport Industry of Comprehensive Transportation Theory (Nanjing Modern Multimodal Transportation Laboratory) (MTF2023004), and the China Postdoctoral Science Foundation (2024T170129, GZC20240261)</arxiv:comment>\n <arxiv:primary_category term='cs.AI'/>\n <author>\n <name>Tianhao Qian</name>\n </author>\n <author>\n <name>Zhuoxuan Li</name>\n </author>\n <author>\n <name>Jinde Cao</name>\n </author>\n <author>\n <name>Xinli Shi</name>\n </author>\n <author>\n <name>Hanjie Liu</name>\n </author>\n <author>\n <name>Leszek Rutkowski</name>\n </author>\n </entry>"
}