ZJLAB-AMMI/LLM4RL
A RL approach to enable cost-effective, intelligent interactions between a local agent and a remote LLM
This project helps operations engineers and researchers studying autonomous agents to manage how an agent interacts with large language models (LLMs). It takes in an agent's task objectives and its environment, and outputs a strategy that significantly reduces the cost and time spent communicating with remote LLMs, while maintaining task performance. This is for anyone building or experimenting with AI agents in environments like robotics or simulation that need to make decisions efficiently.
No commits in the last 6 months.
Use this if you are developing or testing autonomous agents that rely on LLMs for high-level guidance and want to make those interactions more cost-effective and faster.
Not ideal if your agent operates in environments where LLM interaction costs are not a concern, or if you are not using LLMs for task planning.
Stars
79
Forks
13
Language
Python
License
—
Category
Last pushed
Aug 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/ZJLAB-AMMI/LLM4RL"
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