Searching Meta Reasoning Skeleton to Guide LLM Reasoning

Meta reasoning behaviors work as a skeleton to guide large language model (LLM) reasoning, thus help to improve reasoning performance. However, prior researches implement meta reasoning skeleton with manually designed structure, limiting ability to adapt to query-specific requirement and capture intricate logical dependency among reasoning steps. To deal with the challenges, we represent meta reasoning skeleton with directed acyclic graph (DAG) to unify skeletons proposed in prior works and model intricate logical dependency. Then we propose AutoMR, a framework that searches for query-aware meta reasoning skeleton automatically inspired by automated machine learning (AutoML). Specifically, we construct search space based on DAG representation of skeleton and then formulate the search problem. This algorithm can derive any meta reasoning skeleton in search space efficiently and adapt skeleton to evolving base reasoning context, thus enable efficient query-aware skeleton search. We conduct experiments on extensive benchmark datasets. Experimental results show that AutoMR achieves better reasoning performance than previous works broadly. Large language model (LLM) demonstrate superior performance on complex tasks such as math Q&A when equipped with step-by-step reasoning ability (Wei et al., 2022; OpenAI, 2024; DeepSeek-AI, 2025). Researches on cognition divide reasoning into two levels: base reasoning (reasoning for problem directly) and meta reasoning (higher-level reasoning about how to reason) (Flavell, 1979). Meta reasoning, considered a unique ability of human cognition (Ackerman and Thompson, 2017), entails awareness of one's reasoning process and the deliberate selection of reasoning strategies.