Re:Search-R1: Training LLMs to Reason and Leverage Search En...
by 0xlogk on Thursday April 03, 2025 @08:17AM
(#43568556)
The paper mentions they used Wikipedia as search corpus. The repo states they plan to expand to Google, Bing APIs. I wonder how they will handle evolving search corpora, ie. if continual RL updates will be needed.
[ Parent
| on HN ]
There are no comments on this comment yet.