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.

Recent work explores agentic inference-time techniques to perform structured, multi-step reasoning. However, stateless inference often struggles on multi-step tasks due to the absence of persistent state. Moreover, task-specific fine-tuning or instruction-tuning often achieve surface-level code generation but remain brittle on tasks requiring deeper reasoning and long-horizon dependencies. To address these limitations, we propose stateful multi-agent evolutionary search, a training-free framework that departs from prior stateless approaches by combining (i) persistent inference-time state, (ii) adversarial mutation, and (iii) evolutionary preservation. We demonstrate its effectiveness in automated unit test generation through the generation of edge cases. We generate robust edge cases using an evolutionary search process, where specialized agents sequentially propose, mutate, and score candidates. A controller maintains persistent state across generations, while evolutionary preservation ensures diversity and exploration across all possible cases. This yields a generalist agent capable of discovering robust, high-coverage edge cases across unseen codebases. Experiments show our stateful multi-agent inference framework achieves substantial gains in coverage over stateless single-step baselines, evaluated on prevalent unit-testing benchmarks such as HumanEval and TestGenEvalMini and using three diverse LLM families - Llama, Gemma, and GPT. These results indicate that combining persistent inference-time state with evolutionary search materially improves unit-test generation.

Low-discrepancy point sets and digital sequences underpin quasi-Monte Carlo (QMC) methods for high-dimensional integration. We cast two long-standing QMC design problems as program synthesis and solve them with an LLM-guided evolutionary loop that mutates and selects code under task-specific fitness: (i) constructing finite 2D/3D point sets with low star discrepancy, and (ii) choosing Sobol' direction numbers that minimize randomized QMC error on downstream integrands. Our two-phase procedure combines constructive code proposals with iterative numerical refinement. On finite sets, we rediscover known optima in small 2D cases and set new best-known 2D benchmarks for N >= 40, while matching most known 3D optima up to the proven frontier (N <= 8) and reporting improved 3D benchmarks beyond. On digital sequences, evolving Sobol' parameters yields consistent reductions in randomized quasi-Monte Carlo (rQMC) mean-squared error for several 32-dimensional option-pricing tasks relative to widely used Joe--Kuo parameters, while preserving extensibility to any sample size and compatibility with standard randomizations. Taken together, the results demonstrate that LLM-driven evolutionary program synthesis can automate the discovery of high-quality QMC constructions, recovering classical designs where they are optimal and improving them where finite-N structure matters. Data and code are available at https://github.com/hockeyguy123/openevolve-star-discrepancy.git.

Efficient control of prosthetic limbs via non-invasive brain-computer interfaces (BCIs) requires advanced EEG processing, including pre-filtering, feature extraction, and action prediction, performed in real time on edge AI hardware. Achieving this on resource-constrained devices presents challenges in balancing model complexity, computational efficiency, and latency. We present CognitiveArm, an EEG-driven, brain-controlled prosthetic system implemented on embedded AI hardware, achieving real-time operation without compromising accuracy. The system integrates BrainFlow, an open-source library for EEG data acquisition and streaming, with optimized deep learning (DL) models for precise brain signal classification. Using evolutionary search, we identify Pareto-optimal DL configurations through hyperparameter tuning, optimizer analysis, and window selection, analyzed individually and in ensemble configurations. We apply model compression techniques such as pruning and quantization to optimize models for embedded deployment, balancing efficiency and accuracy. We collected an EEG dataset and designed an annotation pipeline enabling precise labeling of brain signals corresponding to specific intended actions, forming the basis for training our optimized DL models. CognitiveArm also supports voice commands for seamless mode switching, enabling control of the prosthetic arm's 3 degrees of freedom (DoF). Running entirely on embedded hardware, it ensures low latency and real-time responsiveness. A full-scale prototype, interfaced with the OpenBCI UltraCortex Mark IV EEG headset, achieved up to 90% accuracy in classifying three core actions (left, right, idle). Voice integration enables multiplexed, variable movement for everyday tasks (e.g., handshake, cup picking), enhancing real-world performance and demonstrating CognitiveArm's potential for advanced prosthetic control.

Hierarchical Evolutionary Agent Simulation (HEAS) is a Python framework that unifies layered agent-based modeling with evolutionary optimization and tournament evaluation in a single, reproducible workflow. HEAS represents models as hierarchies of lightweight processes ("streams") scheduled in deterministic layers that read and write a shared context, making cross-scale couplings explicit and auditable. A compact API and CLI-simulate, optimize, evaluate-expose single- and multi-objective evolution, PyTorch policy integration via parameter flattening/unflattening, and general tournament tooling with user-defined scoring and voting rules. The framework standardizes evaluation through uniform per-step and episode metrics, persists seeds, logbooks, and hall-of-fame archives, and provides plotting helpers for traces, Pareto fronts, and comparative outcomes, reducing glue code and improving comparability across studies. HEAS emphasizes separation of mechanism from orchestration, allowing exogenous drivers, endogenous agents, and aggregators to be composed and swapped without refactoring, while the same model can be used for forward simulation, optimization, or systematic comparison. We illustrate usage with two compact examples-an ecological system and an enterprise decision-making setting. HEAS offers a practical foundation for cross-disciplinary, multi-level inquiry, yielding reliable, reproducible results.

Finding deletion-correcting codes of maximum size has been an open problem for over 70 years, even for a single deletion. In this paper, we propose a novel approach for constructing deletion-correcting codes. A code is a set of sequences satisfying certain constraints, and we construct it by greedily adding the highest-priority sequence according to a priority function. To find good priority functions, we leverage FunSearch, a large language model (LLM)-guided evolutionary search proposed by Romera et al., 2024. FunSearch iteratively generates, evaluates, and refines priority functions to construct large deletion-correcting codes. For a single deletion, our evolutionary search finds functions that construct codes which match known maximum sizes, reach the size of the largest (conjectured optimal) Varshamov-Tenengolts codes where the maximum is unknown, and independently rediscover them in equivalent form. For two deletions, we find functions that construct codes with new best-known sizes for code lengths \( n = 12, 13 \), and \( 16 \), establishing improved lower bounds. These results demonstrate the potential of LLM-guided search for information theory and code design and represent the first application of such methods for constructing error-correcting codes.

Automated feature engineering plays a critical role in improving predictive model performance for tabular learning tasks. Traditional automated feature engineering methods are limited by their reliance on pre-defined transformations within fixed, manually designed search spaces, often neglecting domain knowledge. Recent advances using Large Language Models (LLMs) have enabled the integration of domain knowledge into the feature engineering process. However, existing LLM-based approaches use direct prompting or rely solely on validation scores for feature selection, failing to leverage insights from prior feature discovery experiments or establish meaningful reasoning between feature generation and data-driven performance. To address these challenges, we propose LLM-FE, a novel framework that combines evolutionary search with the domain knowledge and reasoning capabilities of LLMs to automatically discover effective features for tabular learning tasks. LLM-FE formulates feature engineering as a program search problem, where LLMs propose new feature transformation programs iteratively, and data-driven feedback guides the search process. Our results demonstrate that LLM-FE consistently outperforms state-of-the-art baselines, significantly enhancing the performance of tabular prediction models across diverse classification and regression benchmarks.

Structural pruning enhances hardware-agnostic inference efficiency for large language models (LLMs) but often struggles to maintain performance. Local pruning performs efficient layer-by-layer compression but ignores global topology. Global pruning has the potential to find the optimal solution although resource-intensive. However, existing methods tend to rank structural saliency uniformly, ignoring inter-structure dependencies and failing to achieve end-to-end optimization. To address these limitations, we propose T\'yr-the-Pruner, an efficient end-to-end search-based global structural pruning framework. This framework constructs a supernet by repeatedly applying local pruning across a range of sparsity ratios to each layer in an LLM, with the core goal of determining the optimal sparsity distribution under a target overall sparsity ratio. Concretely, we introduce an effective local pruning and an expectation error accumulation approach to improve supernet construction. Furthermore, we employ an iterative prune-and-search strategy with coarse-to-fine sparsity granularity to ensure efficient search convergence. Experimental results show that T\'yr-the-Pruner achieves state-of-the-art structural pruning, retaining 97% of the dense model's performance while removing a challenging 50% of Llama-3.1-70B's parameters.

Neural Architecture Search (NAS) is a powerful automatic alternative to manual design of a neural network. In the zero-shot version, a fast ranking function is used to compare architectures without training them. The outputs of the ranking functions often vary significantly due to different sources of randomness, including the evaluated architecture's weights' initialization or the batch of data used for calculations. A common approach to addressing the variation is to average a ranking function output over several evaluations. We propose taking into account the variation in a different manner, by viewing the ranking function output as a random variable representing a proxy performance metric. During the search process, we strive to construct a stochastic ordering of the performance metrics to determine the best architecture. Our experiments show that the proposed stochastic ordering can effectively boost performance of a search on standard benchmark search spaces.

Weaknesses: v) It is difficult to attribute the source of empirical gains, since the paper is presenting both a problem-specific architecture search space and a particular search method. The comparison to random is missing some potentially-important measures as it has no error bars or plot of the distribution. Though the comparison to evolutionary methods in Fig 2. is a good experiment along these lines, the (missing) random comparison is especially important [a]. The comparison to random is against the *best* model found by random search, instead of error bars or any modeling of the search space. This'd be important for comparisons that separate out the search vs design space as in [a,b].