# InfiGUI-R1

3B GUI agent trained in two stages: distilling spatial reasoning from teacher models, then reinforcement learning that rewards accurate sub-goals and trains error recovery.

- Catalog URL: https://awesomecua.github.io/resources/github-reallm-labs-infigui-r1/
- Original source: https://github.com/Reallm-Labs/InfiGUI-R1
- Kind: model
- Review: curated
- Scope: core
- Environments: cross-platform
- Topics: reinforcement-learning, planning
- Evidence checked: 2026-10-16T06:36:00Z
- ID: github:reallm-labs/infigui-r1

## Limitations

Inclusion does not establish reproducibility or endorsement.

- Record JSON: https://awesomecua.github.io/resources/github-reallm-labs-infigui-r1/record.json

## License declarations

- code: Apache-2.0 — https://raw.githubusercontent.com/Reallm-Labs/InfiGUI-R1/HEAD/LICENSE
- data: not recorded
- document: not recorded
- weights: not recorded

## Primary evidence

- https://raw.githubusercontent.com/Reallm-Labs/InfiGUI-R1/HEAD/README.md (retrieved 2026-10-16T06:36:00Z; SHA-256 5fd1399c88bdf406e7689765ccf0599b3b7e0ddbed082fa92bffdd7b120bd41a)
- https://raw.githubusercontent.com/Reallm-Labs/InfiGUI-R1/HEAD/LICENSE (retrieved 2026-10-16T06:42:01Z; SHA-256 c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4)