nsidn98/LLaMAR
Code for our paper LLaMAR: LM-based Long-Horizon Planner for Multi-Agent Robotics
This project helps robotics engineers and researchers create complex, long-term plans for multiple autonomous robots working together in environments where they can't see everything. It takes high-level natural language instructions and outputs detailed task plans and corrective actions, enabling robots to perform household chores or search and rescue missions more successfully. Robotics engineers and researchers building or deploying multi-agent robotic systems would use this tool.
No commits in the last 6 months.
Use this if you need to program multiple robots to complete multi-step tasks in unpredictable or partially hidden environments without constant human oversight.
Not ideal if your robotic tasks are simple, involve only one robot, or take place in fully visible and controlled environments.
Stars
30
Forks
4
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/nsidn98/LLaMAR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
xrsrke/toolformer
Implementation of Toolformer: Language Models Can Teach Themselves to Use Tools
MozerWang/AMPO
[ICLR 2026] Adaptive Social Learning via Mode Policy Optimization for Language Agents
real-stanford/reflect
[CoRL 2023] REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction
BatsResearch/planetarium
Dataset and benchmark for assessing LLMs in translating natural language descriptions of...
WayneMao/RoboMatrix
The Official Implementation of RoboMatrix