Designing effective heuristics remains a labor-intensive task traditionally reserved for domain experts. While Large Language Model (LLM)-driven evolutionary search offers a path toward automated discovery, existing methods often suffer from slow convergence, primarily due to inefficient hyperparameter tuning. Delegating tuning to specialized optimizers improves performance, but it comes at the cost of code bloat and overfitting. To address these issues, we propose a pipeline that introduces a novel regularization architecture balancing performance and complexity. Specifically, we mitigate the side effects of automated tuning through two novel components: (i) symbolic pruning mutator, which combines LLM semantic guidance with Abstract Syntax Tree analysis to eliminate algorithmic redundancy; and (ii) a complexity-aware mutation gate that explicitly filters out mutations leading to excessive code growth. Our framework substantially accelerates convergence and improves generalization on standard benchmarks of the 3D Single Container Loading Problem. The discovered heuristics match state-of-the-art human designed algorithms and rediscover similar geometric principles used by experts, highlighting the framework's ability to autonomously extract meaningful domain knowledge.

An effective approach for learning both safety constraints and control policies is Inverse Constrained Reinforcement Learning (ICRL). Previous ICRL algorithms commonly employ an online learning framework that permits unlimited sampling from an interactive environment. This setting, however, is infeasible in many realistic applications where data collection is dangerous and expensive. To address this challenge, we propose Inverse Constrained Superior Distribution Correction Estimation (ICSDICE) as an offline ICRL solver. ICSDICE extracts feasible constraints from superior distributions, thereby highlighting policies with expert-exceeding rewards maximization ability. To estimate these distributions, ICSDICE solves a regularized dual optimization problem for safe control by exploiting the observed reward signals and expert preferences. Striving for transferable constraints and unbiased estimations, ICSDICE actively encourages sparsity and incorporates a discounting effect within the learned and observed distributions. Empirical studies show that ICSDICE outperforms other baselines by accurately recovering the constraints and adapting to high-dimensional environments. The code is available at https://github.com/quangr/ICSDICE.