MemGUI-8B-RL

Anonymous release for the ICLR 2027 submission MemGUI-RL: Reinforcement Learning for Proactive Context Management in Long-Horizon Mobile GUI Agents. Project page: https://memgui-rl-anonymous.github.io/

MemGUI-8B-RL is MemGUI-8B-SFT (Qwen3-VL-8B-Instruct supervised on MemGUI-3K) post-trained for 100 optimizer steps with FARPO (Folding-Aware Reward-decoupled Policy Optimization, span-to-step ratio rho = 9). The policy speaks the ConAct (Context-as-Action) interface of MemGUI-Agent: every response contains a folding directive for its own history, an optional memory operation and the next GUI action.

benchmark	MemGUI-8B-SFT	MemGUI-8B-RL
MemGUI-Bench Pass@1 / Pass@3 / IRR (128 tasks)	23.4 / 35.9 / 30.2	24.2 / 43.0 / 35.0
MobileWorld GUI-only success rate (117 tasks, OOD)	17.9	19.7

Usage

The checkpoint is a standard Qwen3VLForConditionalGeneration model (weights in bf16, ~17.5 GB). Use it with the ConAct system prompt and the MemGUI-Agent runtime unchanged:

from transformers import AutoProcessor, Qwen3VLForConditionalGeneration
model = Qwen3VLForConditionalGeneration.from_pretrained("memgui-rl-anonymous/MemGUI-8B-RL", torch_dtype="bfloat16", device_map="auto")
processor = AutoProcessor.from_pretrained("memgui-rl-anonymous/MemGUI-8B-RL")

Training code and launch scripts: https://github.com/memgui-rl-anonymous/MemGUI-RL Training data: https://huggingface.co/datasets/memgui-rl/MemGUI-3K-Verl Evaluation logs: https://huggingface.co/datasets/memgui-rl/MemGUI-RL-Eval