Social deduction games (SDGs) require agents to reason under partial observability by maintaining relational beliefs about hidden roles, team alignments, suspicion, and others’ perceptions. While recent LLM-agent approaches improve gameplay through prompting, reflection, and preference optimization, they often optimize actions and in-game speech without explicitly grounding them in such beliefs. This frequently leads to strategically inconsistent behavior, especially for compact LLM agents. We introduce Multi-Agent Relational Belief Optimization (MARBO), a belief-grounded preference optimization framework that leverages relational beliefs to guide strategic decisions and in-game speech. MARBO selectively provides preference feedback only when behaviors are supported by reliable relational beliefs and lead to strategically favorable social outcomes, encouraging more consistent learning under uncertainty. Experiments on representative SDGs, including Werewolf and Among Us, show that MARBO enables compact LLM agents to consistently outperform existing baselines.