URAI pairs two agents.
Robot agents improve by building and reusing executable motion tools
URAI lets frontier models create, refine and invoke robot-control routines while retaining decision-making between executions.
Top University
Shijia Ge · Alex Zhou · Jianshu Zeng · Yexing Wan · Di Wu · Zelin Zheng · +9 more
Hexafuture Inc. · Peking University · Beijing Institute of Technology · Tsinghua University
Research Digest··3 min read
Ge et al.
Why this paper
From Peking University and 3 others
In one line
URAI improves robot manipulation by letting agents create reusable motion tools, execute them locally, and make model-level decisions between tool calls.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§