Mirroring the Mind: Distilling Human-Like Metacognitive Strategies into Large Language Models
This work addresses the problem of reasoning collapse in Large Reasoning Models for anyone developing or using these models, offering an incremental improvement to their stability and efficiency.
Large Reasoning Models (LRMs) struggle with complex reasoning due to poor self-regulatory control, leading to failures despite valid intermediate steps. The authors propose Metacognitive Behavioral Tuning (MBT), a post-training framework that injects metacognitive behaviors into the model's thought process, resulting in higher accuracy and significantly reduced token consumption on multi-hop QA benchmarks.
Large Reasoning Models (LRMs) often exhibit structural fragility in complex reasoning tasks, failing to produce correct answers even after successfully deriving valid intermediate steps. Through systematic analysis, we observe that these failures frequently stem not from a lack of reasoning capacity, but from a deficiency in self-regulatory control, where valid logic is destabilized by uncontrolled exploration or the failure to recognize logical sufficiency. Motivated by this observation, we propose Metacognitive Behavioral Tuning (MBT), a post-training framework that explicitly injects metacognitive behaviors into the model's thought process. MBT implements this via two complementary formulations: (1) MBT-S, which synthesizes rigorous reasoning traces from scratch, and (2) MBT-R, which rewrites the student's initial traces to stabilize intrinsic exploration patterns. Experiments across multi-hop QA benchmarks demonstrate that MBT consistently outperforms baselines, achieving notable gains on challenging benchmarks. By effectively eliminating reasoning collapse, MBT achieves higher accuracy with significantly reduced token consumption, demonstrating that internalizing metacognitive strategies leads to more stable and robust reasoning.