The development of game agents holds a critical role in advancing towards Artificial General Intelligence (AGI). The progress of LLMs and their multimodal counterparts (MLLMs) offers an unprecedented opportunity to evolve and empower game agents with human-like decision-making capabilities in complex computer game environments. This paper provides a comprehensive overview of LLM-based game agents from a holistic viewpoint. First, we introduce the conceptual architecture of LLM-based game agents, centered around six essential functional components: perception, memory, thinking, role-playing, action, and learning. Second, we survey existing representative LLM-based game agents documented in the literature with respect to methodologies and adaptation agility across six genres of games, including adventure, communication, competition, cooperation, simulation, and crafting & exploration games. Finally, we present an outlook of future research and development directions in this burgeoning field.

Several attempts have been made to implement text command control for game agents. However, current technologies are limited to processing predefined format commands. This paper proposes a pioneering text command control system for a game agent that can understand natural language commands expressed in free-form. The proposed system uses a large language model (LLM) for code generation to interpret and transform natural language commands into behavior branch, a proposed knowledge expression based on behavior trees, which facilitates execution by the game agent. This study conducted empirical validation within a game environment that simulates a Pok\'emon game and involved multiple participants. The results confirmed the system's ability to understand and carry out natural language commands, representing a noteworthy in the realm of real-time language interactive game agents. Notice for the use of this material. The copyright of this material is retained by the Japanese Society for Artificial Intelligence (JSAI). This material is published here with the agreement of JSAI. Please be complied with Copyright Law of Japan if any users wish to reproduce, make derivative work, distribute or make available to the public any part or whole thereof. All Rights Reserved, Copyright (C) The Japanese Society for Artificial Intelligence.

Text-based games(TBG) are complex environments which allow users or computer agents to make textual interactions and achieve game goals.In TBG agent design and training process, balancing the efficiency and performance of the agent models is a major challenge. Finding TBG agent deep learning modules' performance in standardized environments, and testing their performance among different evaluation types is also important for TBG agent research. We constructed a standardized TBG agent with no hand-crafted rules, formally categorized TBG evaluation types, and analyzed selected methods in our environment.

A transfer learning approach is presented to address the challenge of training video game agents with limited data. The approach decomposes games into objects, learns object models, and transfers models from known games to unfamiliar games to guide learning. Experiments show that the approach improves prediction accuracy over a comparable control, leading to more efficient exploration. Training of game agents is thus accelerated by transferring object models from previously learned games.

The novel technique introduced here aims to accomplish the first stage of transferring low-level cognitive skills between two individuals (e.g. from expert to learner) to ease the consecutive higher level declarative learning process for the target "learner" individual in a game environment. Such low-level cognitive skill is associated with the procedural knowledge and established at low-level of mind which can be unveiled and transferred by only a novel technique (rather than by a traditional educational environment ) like a highly interactive computer game domain in which a user exposes his/her unconscious mind behaviors via the game-hero non-deliberately during the game sessions. The cognitive data exposed by the game-hero would be recorded, and then be modelled by the artificial intelligence technique like Bayesian networks for an early stage of cognitive skill transfer and the cognitive stimuli are also generated to be used as game agents to train the learner.

Game agents such as opponents, non-player characters, and teammates are central to player experiences in many modern games. As the landscape of AI techniques used in the games industry evolves to adopt machine learning (ML) more widely, it is vital that the research community learn from the best practices cultivated within the industry over decades creating agents. However, although commercial game agent creation pipelines are more mature than those based on ML, opportunities for improvement still abound. As a foundation for shared progress identifying research opportunities between researchers and practitioners, we interviewed seventeen game agent creators from AAA studios, indie studios, and industrial research labs about the challenges they experienced with their professional workflows. Our study revealed several open challenges ranging from design to implementation and evaluation. We compare with literature from the research community that address the challenges identified and conclude by highlighting promising directions for future research supporting agent creation in the games industry.

Serpent.AI is a simple yet powerful, novel framework to assist developers in the creation of game agents. The framework's raison d'être is first and foremost to provide a valuable tool for Machine Learning & AI research. It also turns out to be ridiculously fun to use as a hobbyist (and dangerously addictive; a fair warning)! The framework features a large assortment of supporting modules that provide solutions to commonly encountered scenarios when using video games as environments as well as CLI tools to accelerate development. It provides some useful conventions but is absolutely NOT opiniated about what you put in your agents: Want to use the latest, cutting-edge deep reinforcement learning algorithm?

The gaming industry has reached a point where improving graphics has only a small effect on how much a player will enjoy a game. The focus has turned to adding more humanlike characteristics into computer game agents. Machine learning techniques are scarcely being used in games, although they do offer powerful means for creating humanlike behaviors in agents. The first person shooter (FPS), Quake 2, is an open source game that offers a multi-agent environment in which to create game agents (bots). The work described in this paper seeks to combine neural networks with a modeling paradigm known as context based reasoning (CxBR) to create a contextual game observation (CONGO) system that produces humanlike Quake 2 bots. A default level of intelligence is instilled into the bots through contextual scripts to prevent the bot from being trained to be completely useless. The results show that the humanness and entertainment value as compared to a traditional scripted bot have improved, although, CONGO bots usually ranked only slightly above a novice skill level. Overall, CONGO offers the gaming community a mode of game play that has promising entertainment value.