Llm Robot Planning Transformer Models

There are 16 llm robot planning models tracked. The highest-rated is xrsrke/toolformer at 48/100 with 144 stars.

Get all 16 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=transformers&subcategory=llm-robot-planning&limit=20"

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

#	Model	Score	Tier	Stars	Language
1	xrsrke/toolformer Implementation of Toolformer: Language Models Can Teach Themselves to Use Tools	48	Emerging	144	Jupyter Notebook
2	MozerWang/AMPO [ICLR 2026] Adaptive Social Learning via Mode Policy Optimization for Language Agents	43	Emerging	48	Python
3	real-stanford/reflect [CoRL 2023] REFLECT: Summarizing Robot Experiences for Failure Explanation...	36	Emerging	103	Jupyter Notebook
4	nsidn98/LLaMAR Code for our paper LLaMAR: LM-based Long-Horizon Planner for Multi-Agent Robotics	35	Emerging	30	Jupyter Notebook
5	BatsResearch/planetarium Dataset and benchmark for assessing LLMs in translating natural language...	35	Emerging	65	Python
6	WayneMao/RoboMatrix The Official Implementation of RoboMatrix	34	Emerging	106	Python
7	Yifan-Song793/ETO Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents...	31	Emerging	159	Python
8	CharlieBrown-v1/KALM [NeurIPS'24] KALM: Knowledgeable Agents by Offline Reinforcement Learning...	30	Emerging	9	Python
9	Human-Centric-Machine-Learning/strategic-ttc Code for "Test-Time Compute Games", 2026	27	Experimental	6	Jupyter Notebook
10	SiyuanHuang95/ManipVQA [IROS24 Oral]ManipVQA: Injecting Robotic Affordance and Physically Grounded...	22	Experimental	102	Python
11	cukurovaai/Benchmarking-LLMs-in-Indoor-Navigation [SIU2025] Implementation of Benchmarking LLM Reasoning in Indoor Robot Navigation	22	Experimental	1	Python
12	ihsan31415/InTeRRoR InTeRRoR: Integrating LLM Output for Robotics Input through Local Wired...	21	Experimental	3	Python
13	MEGARAJAN-S/Large-Action-Model This mini project explores the applications of Large Action Models (LAMs) in...	21	Experimental	1	Python
14	zsychina/verl-python Support `muliti-step` python call in verl. formation:...	18	Experimental	1	Python
15	llmsresearch/aot-plus Implementation of AOT+ method from "LLMs Can Plan Only If We Tell Them"...	17	Experimental	1	Python
16	danghungdo/LLMaE-PPO Initialize PPO agents with expert-like trajectories generated by large...	16	Experimental	—	Jupyter Notebook