cs.CLNov 18, 2026

MIRAGE: A Framework for Multi-hop Reasoning under Dynamic Knowledge Injection

Authors: Heyang Xu, HanWen Hao, Haifeng Wang, Haoyi Zhou, Jianxin Li

Abstract

Multi-hop Question Answering (MQA) requires large language models (LLMs) to retrieve and synthesize multiple pieces of evidence into a coherent reasoning path, which is essential for complex tasks. However, prior work on knowledge updating for MQA has largely focused on simple fact edits, overlooking a more challenging and realistic setting---Knowledge Injection---in which the model must simultaneously accommodate both conflicting updates and entirely novel information. Under this setting, a hop-level answer is often wrong simply because the model trusts the wrong knowledge source: it clings to outdated parametric memory when the injected knowledge conflicts with it (K2), and it cannot answer when the required fact is entirely new (K3). To investigate this, we introduce NEXUS, the first benchmark tailored for multi-hop reasoning under Knowledge Injection, which explicitly covers both conflicting (K2) and incremental (K3) knowledge. We further propose MIRAGE, an efficient, training-free framework whose core component, the Correlation-aware Dual-path Reasoner (CDR), resolves such per-hop source-trust errors via P(True)-based confidence routing, complemented by a lightweight template-guided corrector for residual structural deviations. Extensive experiments across four LLM families and two benchmarks demonstrate that MIRAGE consistently improves both final-answer accuracy and hop-level reasoning accuracy, establishing a new state of the art in this challenging setting.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generation

    Oct 17, 2025Jinliang Liu, Jiale Bai, Shaoning ZengMulti-Hop RAGMulti-Hop QA

  2. KG-Reasoner: A Reinforced Model for End-to-End Multi-Hop Knowledge Graph Reasoning

    Apr 14, 2026Shuai Wang, Yinan YuLLM Reasoning with GraphsGraph Reasoning