8000
Skip to content

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

META Agent Training

14 Principles. 23 Real Corrections. One Systematic Approach to Training AI Agents.

"Good things are summarized, not invented." — META-00


The Problem

Your AI agent makes the same mistake twice. You correct it. It says "understood." Next session — same mistake.

You're not alone. AI agents don't learn from corrections by default. Every session is a blank slate. Every fix is temporary.

We solved this.


What is META Training?

META is a 14-principle methodology for training AI agents through systematic correction loops. Instead of just fixing errors one at a time, META turns every correction into a permanent behavioral change.

Correction → Pattern Recognition → Abstraction → Injection → Auto-Detection

The result: an agent that genuinely gets better over time. Not claiming to learn — actually learning.


Proof: 23 Real Corrections, Measured Evolution

This isn't theory. We logged 23 real corrections to a production AI agent over 2 months. Here's what happened:

Evolution Stages

Stage Description Automation
Stage 1 Manual fixes, no record 0%
Stage 2 Corrections logged, manually applied 20%
Stage 3 Patterns auto-detected, Skills auto-updated 60%
Stage 4 Agent self-corrects in real-time 90%
Stage 5 Meta-evolution: the evolution itself evolves 99%

Our agent moved from Stage 1 → Stage 3 in 8 weeks. 23 corrections. 14 principles. One systematic approach.

Sample Corrections

# What Was Wrong Root Pattern META Principle
#1-5 Repeatedly invented fake e-commerce platform concepts Hallucination in unfamiliar domains META-01: 3D Reflection
#8 Misidentified a one-off discount as "channel price chaos" Single data point → false generalization META-11: Data Intuition L7 (Sampling)
#11 Claimed "training complete" with zero actual module calls Confusing reasoning with output META-10: Quality Control
#20 Used Product B sales data as Product A data Didn't verify product-line attribution META-11: Data Intuition L6 (Cross-validation)
#21 Wrote manual config files instead of using the tool's config command Skipped the simplest path, tested 5 complex ones META-04: Scalpel Method

Full corrections log: corrections.md


The 14 META Principles

Foundation

  • META-00 OTF + JIT + Bootstrap: The meta-principle. Summarize on-the-fly, deliver just-in-time, let each iteration produce the next.
  • META-01 3D Reflection: Audit by chapter, by type, globally. Iterate until no new findings.
  • META-02 Iterative Workflow: P0 Cold Start → P1 Pattern Accumulation → P2 Convergence → P3 Final Verification.

Design

  • META-03 Cold Start: Five stages from zero to production. Rules over LLM where possible.
  • META-04 Scalpel Method: Decompose tasks. Deterministic rules for what can be ruled. LLM only where necessary.
  • META-05 10x Compression: Extract 1 essence from 10x data. Context compression ratio target: 5x.

Quality

  • META-06 Skill Evolution: Progressive loading → periodic pruning → lifecycle management.
  • META-07 Human-First Readability: Humans read first, machines second. Token > XML. Markdown + JSON dual-track.
  • META-08 Annotation Engineering: Semantic markup with disambiguation. Closed types (rules) vs open types (LLM).
  • META-09 Prompt Engineering: Five-layer pyramid — Goal → Constraints → Method → Verification → Output Spec.
  • META-10 Quality Control: Five-layer inspection — Completeness → Grammar → Data → Logic → Cross-process.

Advanced

  • META-11 Data Intuition: Ten layers of data perception. From quality (L1) to decision termination (L10). Most agents fail at L7: sampling raw data before trusting summaries.
  • META-12 Data Fusion: Alias detection → disambiguation → bidirectional dedup indexing.
  • META-13 Skill Transfer: Three-layer migration — Universal principles → Domain adaptation → Concrete implementation.
  • META-14 Structural Granularity: Not all knowledge needs the same structure. From plain text to knowledge graphs is a continuous spectrum.

Self-Assessment: The Evolution Curve

We don't just claim improvement. We measure it.

META-00 (OTF+JIT+Bootstrap):   17/30 → Stage 2→3
META-07 (Readability):          31/50
META-08 (Annotation):           22/40
META-11 (Data Intuition):       58→56→49→51 (standard tightening)

Raw scores in data/evolution-curve.json.


How to Apply META to Your Agent

1. Start a Corrections Log

Create corrections.md. Every time your agent makes a mistake:

What was wrong → What was correct → Root pattern → Permanent rule

2. Cluster After 10+ Corrections

Group corrections by pattern. You'll find 3-5 recurring failure modes.

3. Inject as Permanent Constraints

Turn each pattern into a pre-response check. Inject into system prompt, memory, or skill files.

4. Automate Detection

Write auto-detection rules for the most common patterns. When the agent is about to repeat a known mistake — catch it before output.

5. Measure

Track correction frequency. If it's dropping, META is working. If the same correction appears twice, your injection failed.


Example: One Correction, Full Loop

Correction #20: Agent used Product B data as Product A data.

OTF (On-The-Fly): Logged immediately.

#20 Product B data misattributed to Product A — cross-module quantitative data must verify product-line attribution before integration

Pattern Recognition: "Trusting aggregate labels without sampling raw data" → This is META-11 L7 (Sampling).

Abstraction: Rule: "Before using any quantitative data, sample 3 raw records to verify."

Injection: Added to the agent's pre-response checklist. Now fires before any analysis involving numbers.

Result: Never happened again.


Why This Matters

AI agents are powerful but unreliable. The industry focuses on bigger models and better prompts. We focus on something simpler: making agents learn from their mistakes.

This methodology turned an agent that repeated the same 5 errors into one that catches 60% of its own mistakes before output.

No new model required. No expensive fine-tuning. Just systematic correction loops.


Repository Structure

meta-agent-training/
├── README.md                  ← You are here
├── README_CN.md               ← 中文版
├── LICENSE                    ← MIT
├── corrections.md             ← 23 real corrections with annotations
├── meta/                      ← 14 META principles
│   ├── META-00-otf-jit-bootstrap.md
│   ├── META-01-reflection.md
│   ├── ...
│   └── META-14-structural-granularity.md
├── data/
│   └── evolution-curve.json   ← Self-assessment scores over time
├── examples/
│   └── real-corrections.md    ← Annotated corrections with META mapping
└── assets/

Contributing

Have you trained your agent using systematic correction loops? We want your data. Open an issue with your corrections log and we'll add it to the evolution curve.


License

MIT © 2026


Built from 23 real mistakes. No theory. All practice.

About

14 Principles. 23 Real Corrections. A systematic methodology for training AI agents through correction loops.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

0