MobBench task definitions
A public set of real-device mobile task definitions used to evaluate MobA, with Chinese and English task material packaged in a versioned JSON release.
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
- Benchmarks
- Environment
- android
- Topics
- evaluation, mobile-navigation
- Record publication date
- Not recorded
- Evidence retrieved
- 2026-10-17T12:32:07Z
- Resource ID
- url:b53e03a6e4ca4226d126
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
- cc-by-nc-sa-4.0 (Dataset-card declaration for the MobBench task-definition release only.)
- Document
- Not recorded
- Weights
- Not recorded
License review notes
- Data: Dataset-card declaration for the MobBench task-definition release only. Source 1
Evaluation protocol
- Focus
- mobile task completion
- Setting
- interactive
- Observations
- Android device interface
- Actions / outputs
- mobile GUI actions through a separately configured agent
- Evaluation
- The publisher reports a fifty-task real-device evaluation; the inspected release does not establish an automatic correctness judge.
Scale and counting units
- 50 tasks — MobBench tasks used in the paper source
Task definitions are distinct from device images, agent execution and automated scoring.
Compare source-reviewed profiles
Recorded specifications
- availability
- Ungated v1.0 JSON task-definition file.
- release revision
- 28941d10c49a16efb991d4157e512e14204bf3d6
Explore related topics
Scope and limitations
The ungated manifest lists MobBench_tasks_release_v1.0.json and bilingual cards. The card reports fifty tasks; no sample records were downloaded to recount them. This release supplies task definitions and agent setup guidance, not an independently verified automatic judge or a bundled Android environment. The data card declares CC-BY-NC-SA-4.0; code and model licenses are separate.
Related resources
- documented by: MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation
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 2026-10-17T12:32:07Z. Supports: name, kind, summary, environments, topics, scope, notes, relations, details.benchmark_protocol, licenses.data.
Content fingerprint
231a8f483256c774840c99383ab6536520a0aed0f04d62b4d64f1f59477b906e - editorial primary review
Retrieved 2026-10-17T12:32:07Z. Supports: identity, release_status, details.release_revision.
Content fingerprint
4e7225f956d7cee98fe671e7bfd91fc407d87dd805d8f0c11c3b0c839714ccf3
Suggest a correction
Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.