Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ESG Reporting Lifecycle Management with Large Language Models and AI Agents

Thong Hoang, Mykhailo Klymenko, Xiwei Xu, Shidong Pan, Yi Ding, Xushuo Tang, Zhengyi Yang, Jieke Shi, David Lo

TL;DR

An agentic ESG lifecycle framework that systematically integrates the ESG stages of identification, measurement, reporting, engagement, and improvement is introduced that transforms ESG from a static reporting process into a dynamic, accountable, and adaptive system for sustainability governance.

Abstract

Environmental, Social, and Governance (ESG) standards have been increasingly adopted by organizations to demonstrate accountability towards ethical, social, and sustainability goals. However, generating ESG reports that align with these standards remains challenging due to unstructured data formats, inconsistent terminology, and complex requirements. Existing ESG lifecycles provide guidance for structuring ESG reports but lack the automation, adaptability, and continuous feedback mechanisms needed to address these challenges. To bridge this gap, we introduce an agentic ESG lifecycle framework that systematically integrates the ESG stages of identification, measurement, reporting, engagement, and improvement. In this framework, multiple AI agents extract ESG information, verify ESG performance, and update ESG reports based on organisational outcomes. By embedding agentic components within the ESG lifecycle, the proposed framework transforms ESG from a static reporting process into a dynamic, accountable, and adaptive system for sustainability governance. We further define the technical requirements and quality attributes needed to support four main ESG tasks, such as report validation, multi-report comparison, report generation, and knowledge-base maintenance, and propose three architectural approaches, namely single-model, single-agent, and multi-agent, for addressing these tasks. The source code and data for the prototype of these approaches are available at https://gitlab.com/for_peer_review-group/esg_assistant.

ESG Reporting Lifecycle Management with Large Language Models and AI Agents

TL;DR

An agentic ESG lifecycle framework that systematically integrates the ESG stages of identification, measurement, reporting, engagement, and improvement is introduced that transforms ESG from a static reporting process into a dynamic, accountable, and adaptive system for sustainability governance.

Abstract

Environmental, Social, and Governance (ESG) standards have been increasingly adopted by organizations to demonstrate accountability towards ethical, social, and sustainability goals. However, generating ESG reports that align with these standards remains challenging due to unstructured data formats, inconsistent terminology, and complex requirements. Existing ESG lifecycles provide guidance for structuring ESG reports but lack the automation, adaptability, and continuous feedback mechanisms needed to address these challenges. To bridge this gap, we introduce an agentic ESG lifecycle framework that systematically integrates the ESG stages of identification, measurement, reporting, engagement, and improvement. In this framework, multiple AI agents extract ESG information, verify ESG performance, and update ESG reports based on organisational outcomes. By embedding agentic components within the ESG lifecycle, the proposed framework transforms ESG from a static reporting process into a dynamic, accountable, and adaptive system for sustainability governance. We further define the technical requirements and quality attributes needed to support four main ESG tasks, such as report validation, multi-report comparison, report generation, and knowledge-base maintenance, and propose three architectural approaches, namely single-model, single-agent, and multi-agent, for addressing these tasks. The source code and data for the prototype of these approaches are available at https://gitlab.com/for_peer_review-group/esg_assistant.
Paper Structure (11 sections, 3 figures, 3 tables)

This paper contains 11 sections, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Proposed Framework and ESG Discovery
  3. Proposed Framework
  4. ESG Discovery
  5. An Agentic ESG Lifecycle
  6. Architecture of LLM-based ESG Framework
  7. Functional requirements & Quality attributes
  8. Proposed architectures
  9. Case study
  10. Related Work
  11. Conclusions

Figures (3)

  • Figure 1: Overview of the proposed framework in our research paper.
  • Figure 2: An agentic ESG lifecycle
  • Figure 3: Architectural approaches for an agentic ESG system: single-model (a), single-agent (b), and multi-agent (c). The colors indicate component roles, with purple, dark blue, yellow, and green representing knowledge sources, prompts, LLM-based agentic components, and non-LLM tools and RAG, respectively.