Search papers, labs, and topics across Lattice.
This paper introduces an agentic ESG lifecycle framework that leverages LLMs and AI agents to automate and improve the process of generating ESG reports. The framework systematically integrates ESG stages, including identification, measurement, reporting, engagement, and improvement, by using AI agents to extract information, verify performance, and update reports based on organizational outcomes. The authors evaluate three architectural approaches (single-model, single-agent, and multi-agent) for key ESG tasks like report validation and generation, providing a prototype implementation and dataset.
Automating ESG reporting with LLM-powered agents transforms it from a static compliance exercise into a dynamic, data-driven system for sustainability governance.
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.
