PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering

Abstract

Abstract: Retrieval plays a central role in multi-hop question answering (QA), where answering complex questions requires gathering multiple pieces of evidence. We introduce an Agentic Retrieval System that leverages large language models (LLMs) in a structured loop to retrieve relevant evidence with high precision and recall. Our framework consists of three specialized agents: a Question Analyzer that decomposes a multi-hop question into sub-questions, a Selector that identifies the most relevant context for each sub-question (focusing on precision), and an Adder that brings in any missing evidence (fo

Research Question

Does the robustness of LLMs to irrelevant context in multi-hop QA generalize across different reasoning benchmarks (e.g., MuSiQue, 2WikiMultihopQA) when using large context windows versus iterative retrieval, as measured by F1 and precision under controlled distractor insertion?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance