aimas-upb / aimas-upb/behaviortree-planning-for-ami-agents
Develop small scale atomic intent extraction models for explicit requests
Open
enhancement
- Dominant language
- PDDL
- Stars
- 0
- Forks
- 0
- PR merge metrics
- No merged PRs in 30d
Description
**Explicit request** slot labeling seems doable even for GPT-5 nano, so we have reason to believe that smaller models could do it.
The objective is to evaluate smaller models that can do this for explicit requests, whereby training material is obtained based on the HMAS converted HomeBench benchmark.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.