Soo Ling Lim

Peter J. Bentley, Soo Ling Lim, Paolo Arcaini et al.

The use of autonomous robots for delivery of goods to customers is an exciting new way to provide a reliable and sustainable service. However, in the real world, autonomous robots still require human supervision for safety reasons. We tackle the realworld problem of optimizing autonomous robot timings to maximize deliveries, while ensuring that there are never too many robots running simultaneously so that they can be monitored safely. We assess the use of a recent hybrid machine-learningoptimization approach COIL (constrained optimization in learned latent space) and compare it with a baseline genetic algorithm for the purposes of exploring variations of this problem. We also investigate new methods for improving the speed and efficiency of COIL. We show that only COIL can find valid solutions where appropriate numbers of robots run simultaneously for all problem variations tested. We also show that when COIL has learned its latent representation, it can optimize 10% faster than the GA, making it a good choice for daily re-optimization of robots where delivery requests for each day are allocated to robots while maintaining safe numbers of robots running at once.

Soo Ling Lim, Peter J. Bentley, Randall S. Peterson et al.

Teams are central to human accomplishment. Over the past half-century, psychologists have identified the Big-Five cross-culturally valid personality variables: Neuroticism, Extraversion, Openness, Conscientiousness, and Agreeableness. The first four have shown consistent relationships with team performance. Agreeableness (being harmonious, altruistic, humble, and cooperative), however, has demonstrated a non-significant and highly variable relationship with team performance. We resolve this inconsistency through computational modelling. An agent-based model (ABM) is used to predict the effects of personality traits on teamwork and a genetic algorithm is then used to explore the limits of the ABM in order to discover which traits correlate with best and worst performing teams for a problem with different levels of uncertainty (noise). New dependencies revealed by the exploration are corroborated by analyzing previously-unseen data from one the largest datasets on team performance to date comprising 3,698 individuals in 593 teams working on more than 5,000 group tasks with and without uncertainty, collected over a 10-year period. Our finding is that the dependency between team performance and Agreeableness is moderated by task uncertainty. Combining evolutionary computation with ABMs in this way provides a new methodology for the scientific investigation of teamwork, making new predictions, and improving our understanding of human behaviors. Our results confirm the potential usefulness of computer modelling for developing theory, as well as shedding light on the future of teams as work environments are becoming increasingly fluid and uncertain.

Soo Ling Lim, Peter J. Bentley

If human societies are so complex, then how can we hope to understand them? Artificial Life gives us one answer. The field of Artificial Life comprises a diverse set of introspective studies that largely ask the same questions, albeit from many different perspectives: Why are we here? Who are we? Why do we behave as we do? Starting with the origins of life provides us with fascinating answers to some of these questions. However, some researchers choose to bring their studies closer to the present day. We are after all, human. It has been a few billion years since our ancestors were self-replicating molecules. Thus, more direct studies of ourselves and our human societies can reveal truths that may lead to practical knowledge. The papers in this special issue bring together scientists who choose to perform this kind of research.

Soo Ling Lim, Peter J Bentley, Fuyuki Ishikawa

Conceptual architecture involves a highly creative exploration of novel ideas, often taken from other disciplines as architects consider radical new forms, materials, textures and colors for buildings. While today's generative AI systems can produce remarkable results, they lack the creativity demonstrated for decades by evolutionary algorithms. SCAPE, our proposed tool, combines evolutionary search with generative AI, enabling users to explore creative and good quality designs inspired by their initial input through a simple point and click interface. SCAPE injects randomness into generative AI, and enables memory, making use of the built-in language skills of GPT-4 to vary prompts via text-based mutation and crossover. We demonstrate that compared to DALL-E 3, SCAPE enables a 67% improvement in image novelty, plus improvements in quality and effectiveness of use; we show that in just three iterations SCAPE has a 24% image novelty increase enabling effective exploration, plus optimization of images by users. We use more than 20 independent architects to assess SCAPE, who provide markedly positive feedback.

Peter J. Bentley, Soo Ling Lim, Fuyuki Ishikawa

Agentic LLM AI agents are often little more than autonomous chatbots: actors following scripts, often controlled by an unreliable director. This work introduces a bottom-up framework that situates AI agents in their environment, with all behaviors triggered by changes in their environments. It introduces the notion of aspects, similar to the idea of umwelt, where sets of agents perceive their environment differently to each other, enabling clearer control of information. We provide an illustrative implementation and show that compared to a typical architecture, which leaks up to 83% of the time, aspective agentic AI enables zero information leakage. We anticipate that this concept of specialist agents working efficiently in their own information niches can provide improvements to both security and efficiency.

Peter J. Bentley, Soo Ling Lim, Fuyuki Ishikawa

Large Language Model (LLM) image recognition is a powerful tool for extracting data from images, but accuracy depends on providing sufficient cues in the prompt - requiring a domain expert for specialized tasks. We introduce Cue Learning using Evolution for Accurate Recognition (CLEAR), which uses a combination of LLMs and evolutionary computation to generate and optimize cues such that recognition of specialized features in images is improved. It achieves this by auto-generating a novel domain-specific representation and then using it to optimize suitable textual cues with a genetic algorithm. We apply CLEAR to the real-world task of identifying sustainability data from interior and exterior images of buildings. We investigate the effects of using a variable-length representation compared to fixed-length and show how LLM consistency can be improved by refactoring from categorical to real-valued estimates. We show that CLEAR enables higher accuracy compared to expert human recognition and human-authored prompts in every task with error rates improved by up to two orders of magnitude and an ablation study evincing solution concision.

Peter J Bentley, Soo Ling Lim, Adam Gaier et al.

Constrained optimization problems can be difficult because their search spaces have properties not conducive to search, e.g., multimodality, discontinuities, or deception. To address such difficulties, considerable research has been performed on creating novel evolutionary algorithms or specialized genetic operators. However, if the representation that defined the search space could be altered such that it only permitted valid solutions that satisfied the constraints, the task of finding the optimal would be made more feasible without any need for specialized optimization algorithms. We propose Constrained Optimization in Latent Space (COIL), which uses a VAE to generate a learned latent representation from a dataset comprising samples from the valid region of the search space according to a constraint, thus enabling the optimizer to find the objective in the new space defined by the learned representation. Preliminary experiments show promise: compared to an identical GA using a standard representation that cannot meet the constraints or find fit solutions, COIL with its learned latent representation can perfectly satisfy different types of constraints while finding high-fitness solutions.