mlbio-epfl/LaMer

[ICLR 2026] Meta-RL Induces Exploration in Language Agents

33
/ 100
Emerging

This project helps researchers and developers train large language models (LLMs) to be more adaptive and exploratory when interacting with various environments. By applying a Meta-Reinforcement Learning framework, it allows LLMs to learn how to explore effectively and adapt to new situations on the fly. It is used by AI researchers, machine learning engineers, and computational linguists looking to develop more robust and intelligent language agents.

Use this if you are developing AI agents and want to significantly improve their ability to explore and adapt to new or changing environments.

Not ideal if you are looking for an off-the-shelf application or a tool for general-purpose LLM fine-tuning without a focus on agent exploration and adaptation.

AI-agent-development LLM-training reinforcement-learning-research adaptive-AI computational-linguistics-research
No License No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 5 / 25
Community 11 / 25

How are scores calculated?

Stars

31

Forks

4

Language

Python

License

Last pushed

Feb 01, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/mlbio-epfl/LaMer"

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