Recent breakthroughs in Large Language Models (LLMs) have positioned them as a promising paradigm for agents, with long-term planning and decision-making emerging as core general-purpose capabilities for adapting to diverse scenarios and tasks. Real-time strategy (RTS) games serve as an ideal testbed for evaluating these two capabilities, as their inherent gameplay requires both macro-level strategic planning and micro-level tactical adaptation and action execution. Existing RTS game-based environments either suffer from relatively high computational demands or lack support for textual observations, which has constrained the use of RTS games for LLM evaluation. Motivated by this, we present TowerMind, a novel environment grounded in the tower defense (TD) subgenre of RTS games. TowerMind preserves the key evaluation strengths of RTS games for assessing LLMs, while featuring low computational demands and a multimodal observation space, including pixel-based, textual, and structured game-state representations. In addition, TowerMind supports the evaluation of model hallucination and provides a high degree of customizability. We design five benchmark levels to evaluate several widely used LLMs under different multimodal input settings. The results reveal a clear performance gap between LLMs and human experts across both capability and hallucination dimensions. The experiments further highlight key limitations in LLM behavior, such as inadequate planning validation, a lack of multifinality in decision-making, and inefficient action use. We also evaluate two classic reinforcement learning algorithms: Ape-X DQN and PPO. By offering a lightweight and multimodal design, TowerMind complements the existing RTS game-based environment landscape and introduces a new benchmark for the AI agent field.

Dawei Wang, Di Zhao, Xinyuan Liu, Marci Chi Ma, Xiaoyang Liu, Chengming Zhou, Gary Ushaw, Richard Davison. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

In this paper we propose a solution to delivering scalable realtime physics simulations. Although high performance computing simulations of physics related problems do exist, these are not realtime and do not model the real-time intricate interactions of rigid bodies for visual effect common in video games (favouring accuracy over real-time). As such, this paper presents the first approach to real-time delivery of scalable, commercial grade, video game quality physics. This is achieved by taking the physics engine out of the player's machine and deploying it across standard cloud based infrastructures. The simulation world is then divided into sections that are then allocated to servers. A server maintains the physics for all simulated objects in its section. Our contribution is the ability to maintain a scalable simulation by allowing object interaction across section boundaries using predictive migration techniques. We allow each object to project an aura that is used to determine object migration across servers to ensure seamless physics interactions between objects. The validity of our results is demonstrated through experimentation and benchmarking. Our approach allows player interaction at any point in real-time (influencing the simulation) in the same manner as any video game. We believe that this is the first successful demonstration of scalable real-time physics.

A case study of a computer games engineering course is presented.The course has been designed with close input from industry and is achieving a high rate of success in the number of graduates being recruited by the target industry.The organisers of the course have extensive experience in both the software engineering industry, and in delivering academic teaching.These experiences are combined so that commercial software development practices, technologies and philosophies are adopted throughout the delivery of the academic course.The paper discusses the specifics of how and why this was achieved, and uses the Game Engineering course as an exemplar for encouraging the adoption of commercially inspired techniques within the teaching of software engineering and computer science more generally.

Modern smartphones feature multiple applications which access shared data on the solid state storage within the device. As applications become more complex, contention over this memory resource is becoming an issue. This leads to increased battery drain as the applications are forced to touch the solid state device repeatedly after failing to retrieve or store data due to contention from other applications. We describe an optimistic concurrency control algorithm, combining a novel Read-Write-Validate phase sequence with virtual execution. The protocol is suitable for governing transactions operating on databases residing on resource-constrained devices. Increasing energy efficiency and reducing latency are primary goals for our algorithm. We show that this is achieved by reducing persistent store access, and satisfy real-time requirements via transaction scheduling that affords greater determinism.

This paper reviews developments in general purpose computing on graphics processor units (GPGPU computing) from the perspective of video-game-related artificial intelligence (AI). We present an overview of the field, beginning with early shader language solutions and continuing to discuss three accessible platforms for GPGPU development: CUDA, OpenCL, and Direct Compute. Consideration is given to the commercial and practical realities which hinder the adoption of GPGPU solutions within video game AI, and developments in GPGPU computing directly relevant to common AI practices within the video games industry are reviewed in depth.

A set of ordinary differential equations (ODEs) has been constructed to represent a continuous sigma delta modulator (C/spl Sigma//spl Delta/M) [1], i.e. a continuous equivalent of a conventional sigma delta modulator (/spl Sigma//spl Delta/M). This paper is concerned with a stability analysis of these equations with particular reference being made to values representing the gains of the feedback loop and the integrator leakage in the circuit. Conditions for the stability of the equations representing second and third order modulation are derived. The results from this process are used on a conventional simulation of sigma-delta modulation, and the applicability of this method is discussed. The criteria for stable operation are extended to n/sup th/ order sigma delta modulation and to a generalised architecture for sigma delta modulation. The results are compared to the conditions for stability derived from the work of various authors.>