UI-Genie Agent 7B
A Qwen2.5-VL mobile action model trained using existing and reward-guided synthetic trajectories from the UI-Genie framework.
AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.
What is this resource?
- Resource type
- Models and checkpoints
- Environment
- android
- Topics
- mobile-navigation, imitation-learning, action-prediction
- Record publication date
- Not recorded
- Evidence retrieved
- 2026-10-17T04:03:41Z
- Resource ID
- url:6d959b58bd4a2e98e417
What licenses are recorded?
Code, training data, weights, and documents can have different terms. A blank declaration means unknown, not unrestricted use.
- Code
- Not recorded
- Data
- Not recorded
- Document
- Not recorded
- Weights
- mit (publisher model/dataset card metadata; third-party assets retain their own terms)
Recorded specifications
- disabled
- false
- download url
- https://huggingface.co/HanXiao1999/UI-Genie-Agent-7B/tree/main
- gated
- false
- hub id
- HanXiao1999/UI-Genie-Agent-7B
Explore related topics
Scope and limitations
Four public safetensors shards are present and the card declares MIT. Its training-data metadata/link uses UI-Genie-Agent-5k while prose labels it 16k; no precise training-set relationship or count is asserted across those inconsistent references. Larger announced models are not counted as released.
Related resources
- documented by: UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents
Primary evidence and verification
Source retrieval is separate from experiment reproduction. Use the original publication or publisher page when citing claims about the resource.
- editorial primary review
Retrieved 2026-10-17T04:03:41Z. Supports: name, kind, summary, environments, topics, scope, relations, details.
Content fingerprint
3d4e2deda3e8ecc2e6bbba732c01a84dee2443bb7132ef1aeae444f001d23d69 - editorial primary review
Retrieved 2026-10-17T04:03:41Z. Supports: identity, release_status, details, licenses.weights.
Content fingerprint
20e47378595ed007766a135c37fe6709d8853a780ecd5ef56792f0b88c05aeff - huggingface card
Retrieved 2026-10-17T04:03:41Z. Supports: licenses.weights.
Content fingerprint
3d4e2deda3e8ecc2e6bbba732c01a84dee2443bb7132ef1aeae444f001d23d69
Suggest a correction
Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.