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

[2510.14278] PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2510.14278 (cs) [Submitted on 16 Oct 2025 ( v1 ), last revised 27 Aug 2026 (this version, v2)] Title: PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering Authors: Md Mahadi Hasan Nahid , Davood Rafiei View PDF HTML (experimental) 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. Comments: EMNLP 2026 (long, main) Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) Cite as: arXiv:2510.14278 [cs.CL] (or arXiv:2510.14278v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2510.14278 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Md Mahadi Hasan Nahid [ view email ] [v1] Thu, 16 Oct 2025 04:02:29 UTC (160 KB) [v2] Thu, 27 Aug 2026 18:31:45 UTC (209 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CL < prev | next > new | recent | 2025-10 Change to browse by: cs cs.AI cs.IR References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering#684282
• Predicting Partial Answer Quality and Utility in Agentic Retrieval-Augmented Generation#1110809
• Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval#975116
• SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering#1155222
• When Does Memory Help? A Cost-Aware Evaluation of Long-Term Memory in Tool-Using LLM Agents#972506