# AppSim-Bench

Simulated mobile applications and evaluation tooling for reproducible GUI-agent tasks with controlled application state.

- Catalog URL: https://awesomecua.github.io/resources/github-acrab-agentic-labs-appsim/
- Original source: https://github.com/Acrab-Agentic-Labs/AppSim
- Kind: benchmark
- Review: curated
- Scope: core
- Environments: android
- Topics: evaluation, sandbox
- Evidence checked: 2026-10-16T10:42:12Z
- ID: github:acrab-agentic-labs/appsim

## Limitations

Inclusion does not establish reproducibility or endorsement.

- Record JSON: https://awesomecua.github.io/resources/github-acrab-agentic-labs-appsim/record.json

## Structured profile

- actions: mobile GUI operations
- evaluation: Controlled backend data and outcome-based task verification.
- focus: mobile task completion
- observations: mobile interfaces
- setting: interactive

### Count observations

- 557 tasks — AppSim-Bench paper-described release (reported; source: https://arxiv.org/abs/2609.07712)
- 17 applications — published simulated app set (reported; source: https://raw.githubusercontent.com/Acrab-Agentic-Labs/AppSim/HEAD/README.md)

Use the simulated apps and controlled backend state supplied by the benchmark. Desktop host instructions are not the platform being evaluated.

## License declarations

- code: not recorded
- data: not recorded
- document: not recorded
- weights: not recorded

## Primary evidence

- https://raw.githubusercontent.com/Acrab-Agentic-Labs/AppSim/HEAD/README.md (retrieved 2026-10-16T10:42:12Z; SHA-256 12dc2afe339c1ed66e4a6a4ccf5ae13d27ce32f452960341529a4b9016f69059)
- https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending (retrieved 2026-10-16T06:36:32Z; SHA-256 13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285)