WeiminXiong/IPR

Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement (EMNLP 2024 Main Conference)

30
/ 100
Emerging

This project helps researchers and developers train Large Language Model (LLM) agents to perform complex, multi-step tasks more effectively. It takes expert demonstrations of how to solve a problem and uses an iterative refinement process to teach the LLM agent to follow each step accurately. The output is a more capable LLM agent ready for deployment in environments like online shopping or text-based games.

No commits in the last 6 months.

Use this if you are developing or fine-tuning LLM agents for tasks that require precise, sequential decision-making, such as automated online shopping or interactive problem-solving in text-based environments.

Not ideal if you are looking for an off-the-shelf LLM agent for direct end-user application without any training or development work.

LLM agent training reinforcement learning sequential decision-making automated workflow model refinement
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

66

Forks

9

Language

Python

License

Last pushed

Oct 18, 2024

Commits (30d)

0

Get this data via API

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

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