Pinned Loading

1. verl-agent verl-agent Public

   verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

   Python 1.7k 145

2. DrMAS DrMAS Public

   Dr. MAS is an end-to-end RL training framework for multi-agent LLM systems, supporting the co-training of multiple (heterogeneous) LLMs.

   Python 112 6

3. TimeMaster TimeMaster Public

   Official code for paper "TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning"

   Python 61 5

4. CoSo CoSo Public

   Official code for paper "Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning"

   Python 13 1

5. MLF-DSResNet MLF-DSResNet Public

   This is the implementation of MLF & spiking DS-ResNet

   Python 16 2

6. AgentOCR AgentOCR Public

   AgentOCR is a token-efficient framework that compresses multi-turn agent history by rendering it into images and adopting RL-driven self-compression

   Python 7