This repository is a curated collection of papers and resources focused on enhancing the reasoning capabilities of Large Language Models (LLMs) and Multimodal LLMs. It serves researchers and practitioners interested in techniques like Chain-of-Thought (CoT), exploring emergent reasoning abilities, and applying LLMs to complex problem-solving across text and multimodal domains.

How It Works

The project organizes research papers into categories such as Surveys, Analysis, and specific Techniques (e.g., Chain-of-Thought, Sketch-of-Thought, Self-Correction). It highlights papers that introduce novel methods for improving LLM reasoning, including approaches for multimodal reasoning, scaling reasoning abilities to smaller models, and integrating external tools or symbolic solvers.

Quick Start & Requirements

This is a curated list of research papers and resources, not a runnable software project. No installation or specific requirements are needed to browse the content.

Highlighted Details

• Comprehensive coverage of reasoning techniques, including Chain-of-Thought, Tree of Thoughts, and Self-Correction.
• Dedicated sections for Multimodal Reasoning and Scaling Reasoning in Smaller LLMs.
• Links to papers, code, models, and datasets for many entries.
• Includes surveys and analysis papers providing an overview of the field.

Maintenance & Community

The repository is maintained by "atfortes" and appears to be community-driven, with a "Contributing" section inviting additions and updates. It references other "Awesome Lists" related to LLMs and reasoning.

Licensing & Compatibility

The repository itself does not specify a license. The linked papers are subject to their respective publication licenses and terms.

Limitations & Caveats

This resource is a bibliography and does not provide executable code or pre-trained models directly. The content is a snapshot of research and may not include the very latest advancements.