A feedback-based way to retrieve better RAG context
is a proposed way to choose documents for RAG without depending only on fixed scores. Standard RAG systems often pick documents by checking whether their meaning is close to the user’s question.
That can fail in two ways: a similar-looking document may not help answer the question, and a useful document may be missed because it uses different wording. treats retrieval as a matching process that can change over time.
It uses user feedback and past interactions to learn which documents and ideas were actually useful. It also aims to adjust when user goals change, find links that simple meaning-based matching misses, and improve through small instead of large model .
Key points
- Standard RAG often retrieves documents by meaning .
- Meaning does not always match real usefulness.
- uses user feedback and interaction history to adjust retrieval.
- The approach tries to improve with small instead of full model .
- Better retrieval could reduce wasted for AI agents.