PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering
Read the original on arXiv Computation and Language →PRISM is an agentic retrieval framework that uses large language models in a structured loop to improve evidence gathering for multi‑hop question answering. It splits retrieval into three specialized agents—a Question Analyzer, a Selector focused on precision, and an Adder focused on recall—whose iterative interaction yields a compact yet comprehensive evidence set. Experiments on HotpotQA, 2WikiMultiHopQA, MuSiQue, and MultiHopRAG show that PRISM consistently outperforms strong baselines by achieving higher retrieval accuracy and filtering out distracting content.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.