AI for Climate Finance: Agentic Retrieval and Multi-Step Reasoning for Early Warning System Investments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vaghefi, Saeid Ario, Hachcham, Aymane, Grasso, Veronica, Manicus, Jiska, Msemo, Nakiete, Senni, Chiara Colesanti, Leippold, Markus
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908382541119488
author Vaghefi, Saeid Ario
Hachcham, Aymane
Grasso, Veronica
Manicus, Jiska
Msemo, Nakiete
Senni, Chiara Colesanti
Leippold, Markus
author_facet Vaghefi, Saeid Ario
Hachcham, Aymane
Grasso, Veronica
Manicus, Jiska
Msemo, Nakiete
Senni, Chiara Colesanti
Leippold, Markus
contents Tracking financial investments in climate adaptation is a complex and expertise-intensive task, particularly for Early Warning Systems (EWS), which lack standardized financial reporting across multilateral development banks (MDBs) and funds. To address this challenge, we introduce an LLM-based agentic AI system that integrates contextual retrieval, fine-tuning, and multi-step reasoning to extract relevant financial data, classify investments, and ensure compliance with funding guidelines. Our study focuses on a real-world application: tracking EWS investments in the Climate Risk and Early Warning Systems (CREWS) Fund. We analyze 25 MDB project documents and evaluate multiple AI-driven classification methods, including zero-shot and few-shot learning, fine-tuned transformer-based classifiers, chain-of-thought (CoT) prompting, and an agent-based retrieval-augmented generation (RAG) approach. Our results show that the agent-based RAG approach significantly outperforms other methods, achieving 87\% accuracy, 89\% precision, and 83\% recall. Additionally, we contribute a benchmark dataset and expert-annotated corpus, providing a valuable resource for future research in AI-driven financial tracking and climate finance transparency.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05104
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AI for Climate Finance: Agentic Retrieval and Multi-Step Reasoning for Early Warning System Investments
Vaghefi, Saeid Ario
Hachcham, Aymane
Grasso, Veronica
Manicus, Jiska
Msemo, Nakiete
Senni, Chiara Colesanti
Leippold, Markus
Computation and Language
Tracking financial investments in climate adaptation is a complex and expertise-intensive task, particularly for Early Warning Systems (EWS), which lack standardized financial reporting across multilateral development banks (MDBs) and funds. To address this challenge, we introduce an LLM-based agentic AI system that integrates contextual retrieval, fine-tuning, and multi-step reasoning to extract relevant financial data, classify investments, and ensure compliance with funding guidelines. Our study focuses on a real-world application: tracking EWS investments in the Climate Risk and Early Warning Systems (CREWS) Fund. We analyze 25 MDB project documents and evaluate multiple AI-driven classification methods, including zero-shot and few-shot learning, fine-tuned transformer-based classifiers, chain-of-thought (CoT) prompting, and an agent-based retrieval-augmented generation (RAG) approach. Our results show that the agent-based RAG approach significantly outperforms other methods, achieving 87\% accuracy, 89\% precision, and 83\% recall. Additionally, we contribute a benchmark dataset and expert-annotated corpus, providing a valuable resource for future research in AI-driven financial tracking and climate finance transparency.
title AI for Climate Finance: Agentic Retrieval and Multi-Step Reasoning for Early Warning System Investments
topic Computation and Language
url https://arxiv.org/abs/2504.05104