Position: LLMs Need a Bayesian Meta-Reasoning Framework for More Robust and Generalizable Reasoning

TY - CONF

T1 - Position: LLMs Need a Bayesian Meta-Reasoning Framework for More Robust and Generalizable Reasoning

AU - Yan, Hanqi

AU - Zhang, Linhai

AU - Li, Jiazheng

AU - Shen, Zhenyi

AU - He, Yulan

PY - 2025/5/1

Y1 - 2025/5/1

N2 - Large language models (LLMs) excel in many reasoning tasks but continue to face significant challenges, such as lack of robustness in reasoning, struggling with cross-task generalization, and inefficiencies in scaling up reasoning capabilities. Current training paradigms, including next-token prediction and reinforcement learning from human feedback, often fall short in adaptability to diverse reasoning tasks. Existing approaches, such as prompt optimization and iterative output refinement, offer performance improvement, but can be inefficient and lack effective generalization. To overcome these limitations, this position paper argues for a transformative shift in how LLMs approach reasoning. Drawing inspiration from cognitive science, particularly meta-reasoning theories such as Dual-Process Theory and Metacognitive Reasoning, we propose a Bayesian meta-reasoning framework for LLMs. Our approach integrates self-awareness, monitoring, evaluation, regulation, and meta-reflection, to enhance LLMs’ ability to refine reasoning strategies and generalize across tasks. We revisit existing LLM reasoning methods, identify key challenges, and suggest directions for future research.

AB - Large language models (LLMs) excel in many reasoning tasks but continue to face significant challenges, such as lack of robustness in reasoning, struggling with cross-task generalization, and inefficiencies in scaling up reasoning capabilities. Current training paradigms, including next-token prediction and reinforcement learning from human feedback, often fall short in adaptability to diverse reasoning tasks. Existing approaches, such as prompt optimization and iterative output refinement, offer performance improvement, but can be inefficient and lack effective generalization. To overcome these limitations, this position paper argues for a transformative shift in how LLMs approach reasoning. Drawing inspiration from cognitive science, particularly meta-reasoning theories such as Dual-Process Theory and Metacognitive Reasoning, we propose a Bayesian meta-reasoning framework for LLMs. Our approach integrates self-awareness, monitoring, evaluation, regulation, and meta-reflection, to enhance LLMs’ ability to refine reasoning strategies and generalize across tasks. We revisit existing LLM reasoning methods, identify key challenges, and suggest directions for future research.

KW - meta-reasoning

KW - Large Language Models (LLMs)

KW - Position Paper

M3 - Paper

T2 - 2025 International Conference on Machine Learning

Y2 - 13 July 2025

ER -