We present Lark, a biologically inspired decision-making framework that couples LLM-driven reasoning with an evolutionary, stakeholder-aware Multi-Agent System (MAS). To address verbosity and stakeholder trade-offs, we integrate four mechanisms: (i) plasticity, which applies concise adjustments to candidate solutions; (ii) duplication and maturation, which copy high-performing candidates and specialize them into new modules; (iii) ranked-choice stakeholder aggregation using influence-weighted Borda scoring; and (iv) compute awareness via token-based penalties that reward brevity. The system iteratively proposes diverse strategies, applies plasticity tweaks, simulates stakeholder evaluations, aggregates preferences, selects top candidates, and performs duplication/maturation while factoring compute cost into final scores. In a controlled evaluation over 30 rounds comparing 14 systems, Lark Full achieves a mean rank of 2.55 (95% CI [2.17, 2.93]) and a mean composite score of 29.4/50 (95% CI [26.34, 32.46]), finishing Top-3 in 80% of rounds while remaining cost competitive with leading commercial models ($0.016 per task). Paired Wilcoxon tests confirm that all four mechanisms contribute significantly as ablating duplication/maturation yields the largest deficit (ΔScore = 3.5, Cohen's d_z = 2.53, p < 0.001), followed by plasticity (ΔScore = 3.4, d_z = 1.86), ranked-choice voting (ΔScore = 2.4, d_z = 1.20), and token penalties (ΔScore = 2.2, d_z = 1.63). Rather than a formal Markov Decision Process with constrained optimization, Lark is a practical, compute-aware neuroevolutionary loop that scales stakeholder-aligned strategy generation and makes trade-offs transparent through per-step metrics. Our work presents proof-of-concept findings and invites community feedback as we expand toward real-world validation studies.

--This paper investigates the application of Neuroevo-lution of Augmenting T opologies (NEA T) to automate gameplay in Dark Souls, a notoriously challenging action role-playing game characterized by complex combat mechanics, dynamic environments, and high-dimensional visual inputs. T o facilitate this approach, we introduce the Dark Souls API (DSAPI), a novel Python framework leveraging real-time computer vision techniques for extracting critical game metrics, including player and enemy health states. Using NEA T, agents evolve effective combat strategies for defeating the Asylum Demon, the game's initial boss, without predefined behaviors or domain-specific heuristics. Experimental results demonstrate that evolved agents achieve up to a 35% success rate, indicating the viability of neuroevolution in addressing complex, visually intricate gameplay scenarios. This work represents an interesting application of vision-based neuroevolution, highlighting its potential use in a wide range of challenging game environments lacking direct API support or well-defined state representations. The development of artificial intelligence (AI) capable of playing video games at a human or superhuman level has long been an important benchmark in AI research [1], [2].

One of the common artificial intelligence applications in electronic games consists of making an artificial agent learn how to execute some determined task successfully in a game environment. One way to perform this task is through machine learning algorithms capable of learning the sequence of actions required to win in a given game environment. There are several supervised learning techniques able to learn the correct answer for a problem through examples. However, when learning how to play electronic games, the correct answer might only be known by the end of the game, after all the actions were already taken. Thus, not being possible to measure the accuracy of each individual action to be taken at each time step. A way for dealing with this problem is through Neuroevolution, a method which trains Artificial Neural Networks using evolutionary algorithms. In this article, we introduce a framework for testing optimization algorithms with artificial agent controllers in electronic games, called EvoMan, which is inspired in the action-platformer game Mega Man II. The environment can be configured to run in different experiment modes, as single evolution, coevolution and others. To demonstrate some challenges regarding the proposed platform, as initial experiments we applied Neuroevolution using Genetic Algorithms and the NEAT algorithm, in the context of competitively coevolving two distinct agents in this game.

StarCraft: Brood War remains a challenging benchmark for artificial intelligence research, particularly in the domain of macromanagement, where long-term strategic planning is required. Traditional approaches to StarCraft AI rely on rule-based systems or supervised deep learning, both of which face limitations in adaptability and computational efficiency. In this work, we introduce NeuroPAL, a neuroevolutionary framework that integrates Neuroevolution of Augmenting Topologies (NEAT) with Punctuated Anytime Learning (PAL) to improve the efficiency of evolutionary training. By alternating between frequent, low-fidelity training and periodic, high-fidelity evaluations, PAL enhances the sample efficiency of NEAT, enabling agents to discover effective strategies in fewer training iterations. We evaluate NeuroPAL in a fixed-map, single-race scenario in StarCraft: Brood War and compare its performance to standard NEAT-based training. Our results show that PAL significantly accelerates the learning process, allowing the agent to reach competitive levels of play in approximately half the training time required by NEAT alone. Additionally, the evolved agents exhibit emergent behaviors such as proxy barracks placement and defensive building optimization, strategies commonly used by expert human players. These findings suggest that structured evaluation mechanisms like PAL can enhance the scalability and effectiveness of neuroevolution in complex real-time strategy environments.

Proto-objects - image regions that share common visual properties - offer a promising alternative to traditional attention mechanisms based on rectangular-shaped image patches in neural networks. Although previous work demonstrated that evolving a patch-based hard-attention module alongside a controller network could achieve state-of-the-art performance in visual reinforcement learning tasks, our approach leverages image segmentation to work with higher-level features. By operating on proto-objects rather than fixed patches, we significantly reduce the representational complexity: each image decomposes into fewer proto-objects than regular patches, and each proto-object can be efficiently encoded as a compact feature vector. This enables a substantially smaller self-attention module that processes richer semantic information. Our experiments demonstrate that this proto-object-based approach matches or exceeds the state-of-the-art performance of patch-based implementations with 62% less parameters and 2.6 times less training time.

The choice of neural network features can have a large impact on both the accuracy and speed of the network. Despite the current industry shift towards large transformer models, specialized binary classifiers remain critical for numerous practical applications where computational efficiency and low latency are essential. Neural network features tend to be developed homogeneously, resulting in slower or less accurate networks when testing against multiple datasets. In this paper, we show the effectiveness of Neuvo NAS+ a novel Python implementation of an extended Neural Architecture Search (NAS+) which allows the user to optimise the training parameters of a network as well as the network's architecture. We provide an in-depth analysis of the importance of catering a network's architecture to each dataset. We also describe the design of the Neuvo NAS+ system that selects network features on a task-specific basis including network training hyper-parameters such as the number of epochs and batch size. Results show that the Neuvo NAS+ task-specific approach significantly outperforms several machine learning approaches such as Naive Bayes, C4.5, Support Vector Machine and a standard Artificial Neural Network for solving a range of binary classification problems in terms of accuracy. Our experiments demonstrate substantial diversity in evolved network architectures across different datasets, confirming the value of task-specific optimization. Additionally, Neuvo NAS+ outperforms other evolutionary algorithm optimisers in terms of both accuracy and computational efficiency, showing that properly optimized binary classifiers can match or exceed the performance of more complex models while requiring significantly fewer computational resources.

Activation functions play a critical role in the performance and behaviour of neural networks, significantly impacting their ability to learn and generalise. Traditional activation functions, such as ReLU, sigmoid, and tanh, have been widely used with considerable success. However, these functions may not always provide optimal performance for all tasks and datasets. In this paper, we introduce Neuvo GEAF - an innovative approach leveraging grammatical evolution (GE) to automatically evolve novel activation functions tailored to specific neural network architectures and datasets. Experiments conducted on well-known binary classification datasets show statistically significant improvements in F1-score (between 2.4% and 9.4%) over ReLU using identical network architectures. Notably, these performance gains were achieved without increasing the network's parameter count, supporting the trend toward more efficient neural networks that can operate effectively on resource-constrained edge devices. This paper's findings suggest that evolved activation functions can provide significant performance improvements for compact networks while maintaining energy efficiency during both training and inference phases.

Deep learning models trained on finite data lack a complete understanding of the physical world. On the other hand, physics-informed neural networks (PINNs) are infused with such knowledge through the incorporation of mathematically expressible laws of nature into their training loss function. By complying with physical laws, PINNs provide advantages over purely data-driven models in limited-data regimes. This feature has propelled them to the forefront of scientific machine learning, a domain characterized by scarce and costly data. However, the vision of accurate physics-informed learning comes with significant challenges. This review examines PINNs for the first time in terms of model optimization and generalization, shedding light on the need for new algorithmic advances to overcome issues pertaining to the training speed, precision, and generalizability of today's PINN models. Of particular interest are the gradient-free methods of neuroevolution for optimizing the uniquely complex loss landscapes arising in PINN training. Methods synergizing gradient descent and neuroevolution for discovering bespoke neural architectures and balancing multiple conflicting terms in physics-informed learning objectives are positioned as important avenues for future research. Yet another exciting track is to cast neuroevolution as a meta-learner of generalizable PINN models.

Soft robots can exhibit better performance in specific tasks compared to conventional robots, particularly in healthcare-related tasks. However, the field of soft robotics is still young, and designing them often involves mimicking natural organisms or relying heavily on human experts' creativity. A formal automated design process is required. We propose the use of neuroevolution-based algorithms to automatically design initial sketches of soft actuators that can enable the movement of future medical devices, such as drug-delivering catheters. The actuator morphologies discovered by algorithms like Age-Fitness Pareto Optimization, NeuroEvolution of Augmenting Topologies (NEAT), and Hypercube-based NEAT (HyperNEAT) were compared based on the maximum displacement reached and their robustness against various control methods. Analyzing the results granted the insight that neuroevolution-based algorithms produce better-performing and more robust actuators under different control methods. Moreover, the best-performing morphologies were discovered by the NEAT algorithm. As a future work aspect, we propose using the morphologies discovered here as test beds to optimize specialized controllers, enabling more effective functionality towards the desired deflections of the suggested soft catheters.

The sustainable foraging problem is a dynamic environment testbed for exploring the forms of agent cognition in dealing with social dilemmas in a multi-agent setting. The agents need to resist the temptation of individual rewards through foraging and choose the collective long-term goal of sustainability. We investigate methods of online learning in Neuro-Evolution and Deep Recurrent Q-Networks to enable agents to attempt the problem one-shot as is often required by wicked social problems. We further explore if learning temporal dependencies with Long Short-Term Memory may be able to aid the agents in developing sustainable foraging strategies in the long term. It was found that the integration of Long Short-Term Memory assisted agents in developing sustainable strategies for a single agent, however failed to assist agents in managing the social dilemma that arises in the multi-agent scenario.