by mlbio-epfl · Agent Tool · ★ 31
Meta-RL Induces Exploration in Language Agents Yulun Jiang, Liangze Jiang, Damien Teney, Michael Moor, Maria Brbić This repo contains the source code of 🌊LaMer, a Meta-RL framework of training LLM agents to actively explore and adapt to the environment at test time (ICLR '26). Training To train the LLM Agent with LaMer: To train the LLM Agent with RL baselines: See the folder for more examples. Environment Please follow this note to install and test the agent environments. Acknowledgements This work is built upon verl, verl-agent, reflexion, [RAGEN](https://github.com/mll-lab-nu/RA
| Stars | 31 |
| Forks | 3 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 59.5699057193444/100 |
| Open Issues | 1 |
| Last Updated | 2026-02-01 |
| Created | 2025-12-19 |
| Platforms | python |
| Est. Tokens | ~141k |
These tools work well together with LaMer for enhanced workflows:
Explore other popular agent tool tools:
LaMer is [ICLR 2026] Meta-RL Induces Exploration in Language Agents. It is categorized as a Agent Tool with 31 GitHub stars.
LaMer is primarily written in Python. It covers topics such as iclr2026, large-language-models, llm-agent.
You can find installation instructions and usage details in the LaMer GitHub repository at github.com/mlbio-epfl/LaMer. The project has 31 stars and 3 forks, indicating an active community.