Combinatorial Optimization underpins many real-world applications and yet, de signing performant algorithms to solve these complex, typically NP-hard, problems remains a significant research challenge. Reinforcement Learning (RL) provides a versatile framework for designing heuristics across a broad spectrum of problem domains. However, despite notable progress, RL has not yet supplanted industrial solvers as the go-to solution. Current approaches emphasize pre-training heuristics that construct solutions but often rely on search procedures with limited variance, such as stochastically sampling numerous solutions from a single policy or employing computationally expensive fine-tuning of the policy on individual problem instances. Building on the intuition that performant search at inference time should be anticipated during pre-training, we propose COMPASS, a novel RL approach that parameterizes a distribution of diverse and specialized policies conditioned on a continuous latent space. We evaluate COMPASS across three canonical problems – Travelling Salesman, Capacitated Vehicle Routing, and Job-Shop Scheduling – and demonstrate that our search strategy outperforms state-of-the-art approaches in 9 out of 11 standard benchmarking tasks and generalizes better, surpassing all other approaches on a set of 18 procedurally transformed instance distributions.