MIRROR: Cognitive Inner Monologue Between Conversational Turns for Persistent Reflection and Reasoning in Conversational LLMs

The MIRROR architecture enhances large language models by mimicking human inner monologue through modular reasoning and reflection, comprising a Thinker and Talker system that maintains an internal narrative for improved multi-turn dialogue. Evaluated on safety-critical and complex scenarios, models with MIRROR achieved up to 156% better performance, addressing key failure modes like sycophancy and inconsistency, and significantly outperforming baseline models.