zjunlp/WKM
[NeurIPS 2024] Agent Planning with World Knowledge Model
This project helps improve how AI agents make decisions in complex virtual environments. It takes data from both ideal and problematic agent behaviors, then processes this information to build a 'world knowledge' model. This model then guides the AI agent to plan better and avoid common errors like blindly trying things or generating nonsensical actions, benefiting researchers and developers working on intelligent agents for simulated tasks.
164 stars. No commits in the last 6 months.
Use this if you are developing AI agents for interactive tasks in simulated environments and want them to plan more effectively and reduce errors by incorporating a deeper understanding of the 'world' they operate in.
Not ideal if you are looking for a pre-trained, ready-to-deploy agent for real-world physical tasks or if you don't have existing trajectory data to train the world knowledge model.
Stars
164
Forks
12
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 17, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/zjunlp/WKM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
langfengQ/verl-agent
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is...
sotopia-lab/sotopia
Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)
zhudotexe/redel
ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive...
TIGER-AI-Lab/verl-tool
A version of verl to support diverse tool use
AMAP-ML/Tree-GRPO
[ICLR 2026] Tree Search for LLM Agent Reinforcement Learning