axon-rl/gem
A Gym for Agentic LLMs
This project helps AI researchers and machine learning engineers create and evaluate advanced language models that can learn by interacting with various environments. You provide a large language model and integrate it with a training framework, then use GEM's simulated environments to test how well your model can perform tasks like solving puzzles, answering questions, or writing code. This allows you to develop AI agents that can adapt and improve through experience rather than just static data.
462 stars.
Use this if you are developing or experimenting with agentic large language models and need a standardized, flexible platform to simulate their learning and performance in interactive, complex tasks.
Not ideal if you are looking for a pre-trained, ready-to-deploy LLM for a specific business application or if you are not involved in advanced AI model development and research.
Stars
462
Forks
30
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 21, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/axon-rl/gem"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ai4co/reevo
[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
SALT-NLP/collaborative-gym
Framework and toolkits for building and evaluating collaborative agents that can work together...
Gen-Verse/LatentMAS
Latent Collaboration in Multi-Agent Systems
lean-dojo/LeanCopilot
LLMs as Copilots for Theorem Proving in Lean
WooooDyy/AgentGym-RL
Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon...