frameworks

AI Reasoning Frameworks

This directory contains advanced structured reasoning frameworks for AI language models. Unlike standard prompts that focus on specific tasks, frameworks provide comprehensive methodologies for approaching complex problems, enhancing reasoning capabilities, and improving output quality across multiple domains.

What Are AI Reasoning Frameworks?

AI reasoning frameworks are structured approaches that guide language models through specific cognitive processes. They provide:

1. Structured Thinking: Predefined pathways for processing information
2. Multi-scale Analysis: Approaches to break down complex problems
3. Quality Assurance: Built-in validation and verification steps
4. Enhanced Reasoning: Methods to improve logical consistency
5. Domain Transferability: Techniques that work across multiple fields

These frameworks are particularly valuable when working with complex problems that require structured reasoning, multi-step analysis, or specialized processing methodologies.

When to Use Frameworks vs. Regular Prompts

Use Frameworks When	Use Regular Prompts When
Solving complex, multi-faceted problems	Completing specific, well-defined tasks
Requiring highly structured reasoning	Needing quick, straightforward responses
Working across multiple domains	Focusing on a single domain or task type
Needing consistent methodology	Preferring flexibility in approach
Building reasoning systems	Creating content or performing analysis

Framework Structure

Each framework in this library follows a standardized format:

1. Theoretical Foundation: The underlying principles and theories
2. Processing Layers: The specific cognitive layers or stages
3. Implementation Guide: How to apply the framework in practice
4. Use Cases: Examples of when the framework excels
5. Limitations: Understanding when the framework may not be optimal

Available Frameworks

Context Optimization Frameworks

Revolutionary approaches to prompt engineering:

• Context Engineering - Transform prompts into dynamic, efficient context fields
• ADHD Prompting - Context optimization through cognitive constraint patterns

Decision-Making Frameworks

Frameworks optimized for structured decision processes:

• Enhanced Global Analysis Framework (EGAF) - Cultural adaptability and global problem-solving
• Enhanced Logic-Based Synergistic Framework (ELSF) - Logic and pattern integration

Problem-Solving Frameworks

Frameworks focused on systematic problem decomposition and resolution:

• ECARLM - Elementary Cellular Automata Reasoning for Language Models
• METRICS+ - Layered analytical framework with pattern recognition
• Fractal Framework - Multi-scale hierarchical analysis
• Reasoning v2 - Comprehensive reasoning methodology

Multi-Agent Coordination

Pattern language for systems with 2+ collaborating agents:

• MCPA — Multi-Agent Coordination Pattern Architecture - Routing, shared context, coordination topologies, and evaluation

Framework Comparison

Framework	Key Strength	Best For	Complexity
Context Engineering	Token efficiency & emergence	All prompts - optimization layer	Low-Medium
ADHD Prompting	Clarity through constraint	Token optimization & consistency	Low
ECARLM	Multi-scale state evolution	Complex systems modeling	High
EGAF	Cultural adaptability	Global, multi-domain problems	Medium-High
ELSF	Logic and pattern integration	Technical problem-solving	Medium
Fractal	Structured decomposition	Hierarchical problems	Medium-High
METRICS+	Pattern recognition	Cross-domain insights	Medium
Reasoning v2	Comprehensive reasoning	General problem solving	Medium
MCPA	Multi-agent coordination	Systems with 2+ agents	Medium-High

How to Use These Frameworks

1. Selection: Choose the appropriate framework based on your problem type
2. Implementation: Apply the framework's structure to your specific prompt
3. Execution: Guide the AI through the framework's reasoning processes
4. Validation: Use the framework's built-in validation methods
5. Refinement: Iterate based on results to improve outcomes

Framework Selection Guide

To choose the right framework:

1. Identify your problem type:

   • Is it analytical, creative, or decision-based?
   • Does it require multi-scale thinking?
   • Is formal logic central to the solution?

2. Assess complexity:

   • Simpler problems may not require full frameworks
   • Highly complex problems benefit from structured approaches

3. Consider domain:

   • Some frameworks excel in specific domains
   • Others are designed for cross-domain application

4. Evaluate constraints:

   • Time limitations may favor simpler frameworks
   • Quality requirements may necessitate more complex ones

Creating New Frameworks

When developing new reasoning frameworks:

1. Follow the standardized format with YAML frontmatter
2. Clearly define the theoretical foundation
3. Provide explicit processing stages or layers
4. Include implementation examples
5. Document limitations and ideal use cases
6. Consider how the framework integrates with other approaches

Best Practices

• Framework Combination: Sometimes combining elements from multiple frameworks produces better results
• Simplification: For less complex problems, consider simplified versions of these frameworks
• Documentation: When using a framework, document which aspects were most effective
• Iteration: Frameworks can be refined based on application results
• Context Setting: Always clearly communicate the framework to the AI model

These frameworks represent advanced approaches to enhancing AI reasoning capabilities. By understanding their strengths and appropriate applications, you can significantly improve problem-solving outcomes across a wide range of domains.