# WorkForceAgent-R1

Web-task reward functions, WorkArena data processing and GRPO training configurations for reasoning-oriented language agents.

- Catalog URL: https://awesomecua.github.io/resources/github-night-chen-workforceagent-r1/
- Original source: https://github.com/night-chen/WorkForceAgent-R1
- Kind: framework
- Review: curated
- Scope: core
- Environments: web
- Topics: reinforcement-learning, web-navigation, planning
- Evidence checked: 2026-10-17T02:03:20Z
- ID: github:night-chen/workforceagent-r1

## Limitations

The release contains WorkArena preprocessing and training source. The inspected root has no explicit project license; dependencies retain their own terms. Although the README discusses trained 7B/14B models, it does not provide a verified checkpoint release, so this is cataloged only as a framework.

- Record JSON: https://awesomecua.github.io/resources/github-night-chen-workforceagent-r1/record.json

## License declarations

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

## Primary evidence

- https://raw.githubusercontent.com/night-chen/WorkForceAgent-R1/HEAD/README.md (retrieved 2026-10-17T02:03:20Z; SHA-256 2fb7c0d70ccfa93605d5250a8f6d5182324f0c53d70e1c35ba18cb00f4ada548)
- https://api.github.com/repos/night-chen/WorkForceAgent-R1 (retrieved 2026-10-17T02:03:19Z; SHA-256 0ad3ef1d900200e3ecab86cd44f79038000e8748fb285cdd5f32882455d2e36e)
- https://api.github.com/repos/night-chen/WorkForceAgent-R1/git/trees/main?recursive=1 (retrieved 2026-10-17T02:05:39Z; SHA-256 521d065188a6354416c1aafe88a0eb34486f2c2ec011c1cdf8ed008760dd9c55)