Skip to content

Latest commit

 

History

66 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LLM Post-Training & Agentic RL

A systematic survey of LLM post-training algorithms, industrial practices, and frontier directions.

Read Online Papers Models License: MIT

English | 中文


Overview

Two independent but complementary technical surveys covering 50+ papers and 12+ model technical reports (DeepSeek / Qwen / Kimi / GLM-5, etc.), systematically deconstructing core advances in LLM post-training from 2024–2026.

Post-Training Technical Report

The full algorithm evolution: PPO → GRPO → DAPO → VAPO → CISPO → GSPO → SAPO

Chapter Content
Algorithm Foundations RLHF & RLVR paradigms, derivations and comparisons of 7 core algorithms
Deep Dives Post-training practices of 6 major model families, cross-model insights & data engineering
Trends & Outlook 6 industry consensuses · 5 core challenges · 9 personal perspectives

Agentic RL Survey

RL algorithms for multi-turn interaction, tool use, and long-horizon planning — 47 papers systematically analyzed

Chapter Content
Algorithms & Challenges Reward signals, training stability, exploration efficiency, credit assignment
Landscape & Outlook Technical roadmap analysis · industry observations · future predictions

Quick Start

pip install mkdocs-material pymdown-extensions
mkdocs serve            # http://127.0.0.1:8000

Deploy to GitHub Pages:

mkdocs gh-deploy

Pushing to main also triggers automatic deployment via GitHub Actions.

License

MIT · zhenliang

About

A systematic survey of LLM post-training algorithms, industrial practices, and frontier directions.

Resources

Stars

7 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors