Sumit on Mythryl: “Retrieve What Helps, Only When It Helps: Agentic Reinforcement…”

Retrieve What Helps, Only When It Helps: Agentic Reinforcement Learning for Selective Retrieval-Augmented Machine Translation Uses RL to teach an LLM when to retrieve for translation, and trains the retriever on translation quality, not similarity. 📝 arxiv.org/abs/2610.19528

arxiv.orgRetrieve What Helps, Only When It Helps: Agentic Reinforcement Learning for Selective Retrieval-Augmented Machine TranslationRetrieving external knowledge can improve large language model (LLM) translation by providing supplementary information such as idiom interpretations and terminology. However, existing retrieval-augme...

15/10/26, 5:01 am0 reposts2 likes

Post