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

arXiv:2510.14278v2 Announce Type: replace Abstract: Retrieval plays a central role in multi-hop question answering (QA), where answering complex questions requires gathering multiple pieces of evidence. We propose PRISM, an agentic retrieval framework that leverages large language models (LLMs) in a structured loop to retrieve relevant evidence with high precision and recall. PRISM decomposes retrieval into three specialized agents: a Question Analyzer that breaks complex queries 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 (focusing on recall). The iterative interaction between the Selector and Adder produces a compact yet comprehensive evidence set, avoiding both brittle error propagation and noisy context accumulation. It achieves higher retrieval accuracy while filtering out distracting content, enabling downstream QA models to surpass full-context answer accuracy while relying on significantly less irrelevant information. Experiments on four challenging multi-hop QA benchmarks, including HotpotQA, 2WikiMultiHopQA, MuSiQue, and MultiHopRAG, demonstrate that our approach consistently outperforms strong baselines.

Related

• DocNavRAG: Document-Structured Graph RAG with Stateful Evidence Construction for Complex Document Question Answering
• GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory Curriculum
• Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering
• MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA
• Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning

Source: arXiv cs.CL | 2026-08-31