Update README.md

This commit is contained in:
PSBigBig × MiniPS 2026-02-26 11:40:37 +08:00 committed by GitHub
parent 55c6307270
commit df32afc73d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -112,12 +112,14 @@ When reasoning from this page:
| [Awesome Data Science academic](https://github.com/academic/awesome-datascience) | [![GitHub Repo stars](https://img.shields.io/github/stars/academic/awesome-datascience?style=social)](https://github.com/academic/awesome-datascience) | Lists WFGY as a reference for LLM and RAG diagnostic workflows in data science infrastructure. |
| [Awesome-AITools](https://github.com/ikaijua/Awesome-AITools) | [![GitHub Repo stars](https://img.shields.io/github/stars/ikaijua/Awesome-AITools?style=social)](https://github.com/ikaijua/Awesome-AITools) | Lists WFGY ProblemMap as an open-source RAG failure-mode checklist and diagnostics toolkit for LLM pipelines (data, embeddings, retrievers, tools, evaluation). |
| [Awesome AI in Finance](https://github.com/georgezouq/awesome-ai-in-finance) | [![GitHub Repo stars](https://img.shields.io/github/stars/georgezouq/awesome-ai-in-finance?style=social)](https://github.com/georgezouq/awesome-ai-in-finance) | Lists WFGY as a tool for stress testing and validating RAG-based financial systems. |
| [awesome-agentic-patterns](https://github.com/nibzard/awesome-agentic-patterns) | [![GitHub Repo stars](https://img.shields.io/github/stars/nibzard/awesome-agentic-patterns?style=social)](https://github.com/nibzard/awesome-agentic-patterns) | Adds the **Reliability Problem Map Checklist for RAG and Agents** pattern in the Reliability & Eval category, based on the WFGY ProblemMap and linking back to WFGY as a reliability checklist for RAG-heavy agents. |
| [Awesome AI Books](https://github.com/zslucky/awesome-ai-books) | [![GitHub Repo stars](https://img.shields.io/github/stars/zslucky/awesome-ai-books?style=social)](https://github.com/zslucky/awesome-ai-books) | Mentions the WFGY TXT and PDF packs in the LLM reading list. |
| [Awesome AI Web Search (discussion 15)](https://github.com/felladrin/awesome-ai-web-search/discussions/15) | [![GitHub Repo stars](https://img.shields.io/github/stars/felladrin/awesome-ai-web-search?style=social)](https://github.com/felladrin/awesome-ai-web-search) | Discusses the 16 mode map as a candidate taxonomy for RAG failure modes in web search agents. |
| [Awesome AI System](https://github.com/lambda7xx/awesome-AI-system) | [![GitHub Repo stars](https://img.shields.io/github/stars/lambda7xx/awesome-AI-system?style=social)](https://github.com/lambda7xx/awesome-AI-system) | Lists WFGY under LLM robustness and debugging infrastructure. |
| [Awesome AI Tools](https://github.com/eudk/awesome-ai-tools) | [![GitHub Repo stars](https://img.shields.io/github/stars/eudk/awesome-ai-tools?style=social)](https://github.com/eudk/awesome-ai-tools) | Includes WFGY as an open-source framework for debugging LLM agents and RAG pipelines. |
| [AI Agents for Cybersecurity](https://github.com/santosomar/AI-agents-for-cybersecurity) | [![GitHub Repo stars](https://img.shields.io/github/stars/santosomar/AI-agents-for-cybersecurity?style=social)](https://github.com/santosomar/AI-agents-for-cybersecurity) | References the 16 mode map as a debugging guide for RAG-heavy security agents. |
| [Awesome Artificial Intelligence Research](https://github.com/ThyrixYang/awesome-artificial-intelligence-research) | [![GitHub Repo stars](https://img.shields.io/github/stars/ThyrixYang/awesome-artificial-intelligence-research?style=social)](https://github.com/ThyrixYang/awesome-artificial-intelligence-research) | Links to WFGY in the NLP section as a project on LLM robustness, debugging, and reliability. |
| [Awesome-LLM-based-Evaluators](https://github.com/dependentsign/Awesome-LLM-based-Evaluators) | [![GitHub Repo stars](https://img.shields.io/github/stars/dependentsign/Awesome-LLM-based-Evaluators?style=social)](https://github.com/dependentsign/Awesome-LLM-based-Evaluators) | Lists **WFGY 3.0 · Singularity Demo** and the **WFGY ProblemMap** in its “Robustness & stress-test resources” section as a TXT-based long-horizon tension reasoning benchmark and failure map for RAG / LLM robustness evaluation. |
> If your project uses the WFGY ProblemMap and you would like to be listed here, feel free to open an issue or pull request.