{"ID":2853856,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.15259","arxiv_id":"2510.15259","title":"SAG-Agent: Enabling Long-Horizon Reasoning in Strategy Games via Dynamic Knowledge Graphs","abstract":"Most commodity software lacks accessible Application Programming Interfaces (APIs), requiring autonomous agents to interact solely through pixel-based Graphical User Interfaces (GUIs). In this API-free setting, large language model (LLM)-based agents face severe efficiency bottlenecks: limited to local visual experiences, they make myopic decisions and rely on inefficient trial-and-error, hindering both skill acquisition and long-horizon planning. To overcome these limitations, we propose SAG-Agent, an experience-driven learning framework that structures an agent's raw pixel-level interactions into a persistent State-Action Graph (SAG). SAG-Agent mitigates inefficient exploration by topologically linking functionally similar but visually distinct GUI states, constructing a rich neighborhood of experience that enables the agent to generalize from a diverse set of historical strategies. To facilitate long-horizon reasoning, we design a novel hybrid intrinsic reward mechanism based on the graph topology, combining a state-value reward for exploiting known high-value pathways with a novelty reward that encourages targeted exploration. This approach decouples strategic planning from pure discovery, allowing the agent to effectively value setup actions with delayed gratification. We evaluate SAG-Agent in two complex, open-ended GUI-based decision-making environments (Civilization V and Slay the Spire), demonstrating significant improvements in exploration efficiency and strategic depth over the state-of-the-art methods.","short_abstract":"Most commodity software lacks accessible Application Programming Interfaces (APIs), requiring autonomous agents to interact solely through pixel-based Graphical User Interfaces (GUIs). In this API-free setting, large language model (LLM)-based agents face severe efficiency bottlenecks: limited to local visual experienc...","url_abs":"https://arxiv.org/abs/2510.15259","url_pdf":"https://arxiv.org/pdf/2510.15259v3","authors":"[\"Chenwei Tang\",\"Lin Long\",\"Xinyu Liu\",\"Jingyu Xing\",\"Zizhou Wang\",\"Joey Tianyi Zhou\",\"Jiawei Du\",\"Liangli Zhen\",\"Jiancheng Lv\"]","published":"2025-10-17T02:53:06Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}