WeiminXiong/MPO

MPO: Boosting LLM Agents with Meta Plan Optimization (EMNLP 2025 Findings)

35
/ 100
Emerging

This project helps AI developers and researchers create more effective large language model (LLM) agents by improving their ability to plan complex tasks. It takes general, high-level guidance as input and produces optimized plans that lead to better task execution by the agent. This is designed for those building and evaluating advanced AI agents.

No commits in the last 6 months.

Use this if you are developing LLM agents and need a way to enhance their planning capabilities without extensive manual effort in providing detailed instructions.

Not ideal if you are looking for an off-the-shelf application that solves a specific end-user problem, as this is a framework for agent development.

AI agent development LLM fine-tuning task planning AI research autonomous systems
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

76

Forks

4

Language

Python

License

Apache-2.0

Last pushed

Aug 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/WeiminXiong/MPO"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.