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

arXiv: https://arxiv.org/abs/2510.14278 · HTML: https://mlsanity.com/paper/2510.14278/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 29 of 29)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries](https://mlsanity.com/paper/2401.15391/) (2024)
- [RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs](https://mlsanity.com/paper/2407.02485/) (2024)
- [Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval](https://mlsanity.com/paper/2009.12756/) (2020)
- [RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!](https://mlsanity.com/paper/2312.02724/) (2023)
- [Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering](https://mlsanity.com/paper/1911.10470/) (2019)
- [Multi-hop Reading Comprehension through Question Decomposition and Rescoring](https://mlsanity.com/paper/1906.02916/) (2019)
- [On the Theoretical Limitations of Embedding-Based Retrieval](https://mlsanity.com/paper/2508.21038/) (2025)
- [Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems](https://mlsanity.com/paper/2407.01370/) (2024)
- [Answering Complex Open-domain Questions Through Iterative Query Generation](https://mlsanity.com/paper/1910.07000/) (2019)
- [Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable](https://mlsanity.com/paper/2110.13472/) (2021)
- [Shifting from Ranking to Set Selection for Retrieval Augmented Generation](https://mlsanity.com/paper/2507.06838/) (2025)
- [Can we Retrieve Everything All at Once? ARM: An Alignment-Oriented LLM-based Retrieval Method](https://mlsanity.com/paper/2501.18539/) (2025)
- [ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervision](https://mlsanity.com/paper/2505.21250/) (2025)

## Built on by (most cited first, 8 of 8)

- [When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering](https://mlsanity.com/paper/2601.19827/) (2026)
- [State-Centric Decision Process](https://mlsanity.com/paper/2605.12755/) (2026)
- [DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking](https://mlsanity.com/paper/2605.18767/) (2026)
- [LLM-Guided Planning for Multi-hop Reasoning over Multimodal Nuclear Regulatory Documents](https://mlsanity.com/paper/2606.29399/) (2026)
- [THOR: A Theta-Gamma Hierarchical Oscillatory Reasoning Framework for Multi-hop QA](https://mlsanity.com/paper/2607.20459/) (2026)
- [PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding](https://mlsanity.com/paper/2608.24082/) (2026)
- [Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents](https://mlsanity.com/paper/2609.37236/) (2026)
- [Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice](https://mlsanity.com/paper/2610.10590/) (2026)

## Abstract (arXiv)

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.