Awesome-LLM-Reasoning
This resource provides a curated collection of research papers and tools aimed at examining and enhancing the reasoning abilities of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs). It covers recent surveys, analysis, and methodologies regarding LLM reasoning, addressing aspects like mathematical reasoning and emergent phenomena. The repository includes significant studies on internal consistency, token bias, and multi-hop reasoning, offering code samples and theoretical insights. Researchers and developers can explore techniques such as Chain-of-Thought reasoning and assess how LLMs develop new research concepts, thus advancing AI's logical thinking frontiers.