# Knowledge-Grounded Agentic Large Language Models for Multi-Hazard Understanding from Reconnaissance Reports

arXiv: https://arxiv.org/abs/2511.14010 · HTML: https://mlsanity.com/paper/2511.14010/

## Key facts

- Cited by 2 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 24 of its 58 references that are in the map.
- First posted on arXiv 18 Nov 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, 24 of 24)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs](https://mlsanity.com/paper/2407.02485/) (2024)
- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [Sufficient Context: A New Lens on Retrieval Augmented Generation Systems](https://mlsanity.com/paper/2411.06037/) (2024)
- [Financial Report Chunking for Effective Retrieval Augmented Generation](https://mlsanity.com/paper/2402.05131/) (2024)
- [MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation](https://mlsanity.com/paper/2501.00332/) (2024)
- [Evaluating Open-QA Evaluation](https://mlsanity.com/paper/2305.12421/) (2023)
- [chatClimate: Grounding Conversational AI in Climate Science](https://mlsanity.com/paper/2304.05510/) (2023)
- [Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset Analysis](https://mlsanity.com/paper/2505.21700/) (2025)
- [Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation](https://mlsanity.com/paper/2404.06910/) (2024)
- [HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.04800/) (2025)
- [Result Diversification in Search and Recommendation: A Survey](https://mlsanity.com/paper/2212.14464/) (2022)
- [KG-LLM-Bench: A Scalable Benchmark for Evaluating LLM Reasoning on Textualized Knowledge Graphs](https://mlsanity.com/paper/2504.07087/) (2025)
- [Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey](https://mlsanity.com/paper/2505.03418/) (2025)
- [A Survey of Long-Document Retrieval in the PLM and LLM Era](https://mlsanity.com/paper/2509.07759/) (2025)
- [Responsible Retrieval Augmented Generation for Climate Decision Making from Documents](https://mlsanity.com/paper/2410.23902/) (2024)
- [Automatic Question & Answer Generation Using Generative Large Language Model (LLM)](https://mlsanity.com/paper/2508.19475/) (2025)
- [CyPortQA: Benchmarking Multimodal Large Language Models for Cyclone Preparedness in Port Operation](https://mlsanity.com/paper/2508.15846/) (2025)
- [Towards fully automated post-event data collection and analysis: pre-event and post-event information fusion](https://mlsanity.com/paper/1907.05285/) (2019)

## Built on by (most cited first, 2 of 2)

- [Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models](https://mlsanity.com/paper/2604.12185/) (2026)
- [DisasterBench: A Multimodal Benchmark for UAV-Based Disaster Response in Complex Environments](https://mlsanity.com/paper/2606.06217/) (2026)

## Abstract (arXiv)

Post-disaster reconnaissance reports contain critical evidence for understanding multi-hazard interactions, yet their unstructured narratives make systematic knowledge transfer difficult. Large language models (LLMs) offer new potential for analyzing these reports, but often generate unreliable or hallucinated outputs when domain grounding is absent. This study introduces the Mixture-of-Retrieval Agentic RAG (MoRA-RAG), a knowledge-grounded LLM framework that transforms reconnaissance reports into a structured foundation for multi-hazard reasoning. The framework integrates a Mixture-of-Retrieval mechanism that dynamically routes queries across hazard-specific databases while using agentic chunking to preserve contextual coherence during retrieval. It also includes a verification loop that assesses evidence sufficiency, refines queries, and initiates targeted searches when information remains incomplete. We construct HazardRecQA by deriving question-answer pairs from GEER reconnaissance reports, which document 90 global events across seven major hazard types. MoRA-RAG achieves up to 94.5 percent accuracy, outperforming zero-shot LLMs by 30 percent and state-of-the-art RAG systems by 10 percent, while reducing hallucinations across diverse LLM architectures. MoRA-RAG also enables open-weight LLMs to achieve performance comparable to proprietary models. It establishes a new paradigm for transforming post-disaster documentation into actionable, trustworthy intelligence for hazard resilience.