ESG Reporting Lifecycle Management with Large Language Models and AI Agents

2026-03-11

AI Summary

This study addresses key challenges in ESG reporting—namely unstructured data, inconsistent terminology, and complex regulatory standards—compounded by the absence of automation and dynamic feedback in current workflows. To overcome these limitations, this work proposes the first AI-driven, multi-agent framework for end-to-end ESG lifecycle management, systematically integrating five phases: identification, measurement, reporting, stakeholder engagement, and continuous improvement. The framework enables a shift from static disclosure to adaptive, accountable governance by leveraging large language models within three agent configurations: single-model, single-agent, and multi-agent. It supports automated report generation, cross-validation, multi-version comparison, and knowledge base maintenance. A prototype implementation demonstrates significant improvements in report consistency, accuracy, and adaptability, with code and data publicly released.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• ESG reporting
• unstructured data
• inconsistent terminology
• complex requirements
• lifecycle management

Innovation

• AI agents
• Large Language Models
• ESG reporting
• Agentic framework
• Sustainability governance