WxxShirley/GNN4TaskPlan
[NeurIPS 2024] Official implementation for paper "Can Graph Learning Improve Planning in LLM-based Agents?"
This project helps integrate Graph Neural Networks (GNNs) with Large Language Models (LLMs) to improve how LLMs plan and break down complex user requests into actionable steps. It takes a complex user request as input and outputs a more efficient, accurate sequence of sub-tasks for the LLM to execute. This is for AI researchers and developers working on building more robust and reliable LLM-based agents.
151 stars. No commits in the last 6 months.
Use this if you are developing LLM-based agents and find that current LLMs struggle with complex decision-making and planning, especially when sub-tasks have dependencies that can be modeled as a graph.
Not ideal if you are looking for a plug-and-play solution for general-purpose LLM improvements without diving into graph-based planning or agent architecture.
Stars
151
Forks
12
Language
Python
License
MIT
Category
Last pushed
May 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/WxxShirley/GNN4TaskPlan"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AMAP-ML/Tree-GRPO
[ICLR 2026] Tree Search for LLM Agent Reinforcement Learning
xrsrke/toolformer
Implementation of Toolformer: Language Models Can Teach Themselves to Use Tools
Auromix/ROS-LLM
ROS-LLM is a framework designed for embodied intelligence applications in ROS. It allows natural...
xingyaoww/code-act
Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao...
MozerWang/AMPO
[ICLR 2026] Adaptive Social Learning via Mode Policy Optimization for Language Agents