In response to the increasing complexity of modern products, dynamic markets, and intensified competition, project‐based organizations are actively seeking methodologies to efficiently manage their expanding project portfolios. This paper analyzes the project portfolio selection problem in uncertain environments. Despite recent advances in the field, there is a pressing need for decision‐making frameworks that blend optimization and simulation with realistic project information and portfolio constraints. Through an extensive literature review, we identify key variables critical for handling practical scenarios, such as project schedule interdependencies, duration estimations across various scenarios, baseline budget, risk registers, interproject correlations, and cost overrun correlation. To tackle the inherent stochasticity, we introduce a simheuristic algorithm that combines genetic optimization with Monte Carlo simulation. This strategy maximizes the expected value while adhering to project and portfolio constraints under a set portfolio budget reliability level. This approach provides decision‐makers with a powerful tool for enhancing project selection processes, promoting upfront planning, improving risk management, and the achievement of strategic goals. The performance of this approach is validated against deterministic methodologies, such as employing a mixed‐integer linear programming solver in stochastic environments, demonstrating its effectiveness and practical applicability.

In many real-world domains, optimization problems involve both quantitative objectives and qualitative criteria that cannot be directly formulated as mathematical functions. While recent research has integrated large language models (LLMs) into optimization algorithms, these approaches primarily use LLMs to guide the search process, generate heuristics, or tune optimization strategies, rather than to evaluate semantic objectives. This paper introduces generative heuristics, a methodology that combines traditional metaheuristics with LLM-based semantic evaluation to address ‘soft optimization’ problems containing both hard quantitative constraints and soft qualitative objectives. The proposed methodology first applies a metaheuristic algorithm to generate a shortlist of high-quality candidate solutions satisfying the quantitative objectives. These candidates are then evaluated by an LLM according to a user-defined qualitative rubric, and the resulting semantic scores are incorporated into the optimization process through a weighted soft objective. The methodology is illustrated through a constrained portfolio optimization problem in which financial risk is minimized while simultaneously promoting strategic objectives related to sector diversification, geographic exposure, environmental-social-governance quality, and overall portfolio coherence. Experimental results show that the proposed methodology consistently improves strategic alignment while producing solutions that remain close to those obtained from the hard optimization formulation.