The authors built a closed-loop development framework around a shared action–feedback–verification contract.
Closed-loop development improves mobile agents across planning and tool use
The authors connect agent-generated data, reinforcement learning, and runtime feedback to jointly improve a mobile planning model and its execution harness.
Independent
Tingyu Qu · Weigao Sun · Yuecheng Liu · Yucheng Zhao · Yi Zhu · Yifeng Ding · +20 more
Research Digest··2 min read
Thread:Agent Harness Optimization
Qu et al.
Why this paper
Independent · Part of Agent Harness Optimization, now 61 papers
In one line
Qwen-Planner-Agent achieves the best overall performance on MobilePA-Bench through a closed-loop AI-for-AI framework.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§