I tried to do it based on ICLR conference, and rank via LLM-tournament, see result https://openreview-copilot.eamag.me/projects and process https://eamag.me/2025/Paper-To-Project
[1] https://www.semanticscholar.org/paper/A-Review-of-LLM-Assist...
Except when I have access to the right ears I force some measurable success metrics at the beginning to maintain scope stability after agreements.
Except when I have access to the right ears I force some measurable success metrics at the beginning to maintain scope stability after agreements.