ESG Reporting Lifecycle Management with Large Language Models and AI Agents

• URL: http://arxiv.org/abs/2603.10646v1
• Date: Wed, 11 Mar 2026 11:05:58 GMT
• Title: ESG Reporting Lifecycle Management with Large Language Models and AI Agents
• Abstract summary: Existing ESG lifecycles provide guidance for structuring ESG reports but lack the automation, adaptability, and continuous feedback mechanisms needed to address these challenges.<n>We introduce an agentic ESG lifecycle framework that systematically integrates the ESG stages of identification, measurement, reporting, engagement, and improvement.<n>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.
• Score: 16.29132444167956
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Benchmarking Embedding Models for ESG Data [0.5708902722746041]
  Embedding models have emerged as a powerful approach for transforming unstructured ESG text into numerical representations.<n>We benchmark fourteen models, both open-source and closed-source embedding models, comparing their performance with respect to retrieval, and Retrieval-Augmented Generation (RAG)<n>The results demonstrate performance variations across different models, with Qwen3-based models achieving the highest overall performance.
  arXiv  Detail & Related papers  (2026-09-14T11:59:58Z)
• Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agents [68.52563127206808]
  Structure-aware Retrieval Augmented Generation (SA-RAG) uses tables as an intermediate structured representation to provide a compact and controllable interface.<n>We introduce a quality-aware table metadata generation framework that models metadata normalization and effectiveness.<n>Experiments on two noisy real-world datasets show that SA-RAG significantly outperforms existing RAG baselines.
  arXiv  Detail & Related papers  (2026-05-23T03:07:33Z)
• ESG-Bench: Benchmarking Long-Context ESG Reports for Hallucination Mitigation [13.314189556503054]
  This paper introduces ESG-Bench, a benchmark dataset for ESG report understanding and hallucination mitigation in large language models (LLMs)<n>ESG-Bench contains human-annotated question-answer pairs grounded in real-world ESG report contexts.<n>We design task-specific Chain-of-Thought prompting strategies and fine-tune multiple state-of-the-art LLMs on ESG-Bench using CoT-annotated rationales.
  arXiv  Detail & Related papers  (2026-03-13T16:48:05Z)
• Multi-Step Semantic Reasoning in Generative Retrieval [50.65947993017158]
  Generative retrieval (GR) models encode a corpus within model parameters and generate relevant document identifiers for a given query.<n>Existing GR models struggle with complex queries in numerical contexts, such as those involving semantic reasoning over financial reports.<n>We propose ReasonGR, a framework designed to enhance multi-step semantic reasoning in numerical contexts within GR.
  arXiv  Detail & Related papers  (2026-03-12T18:38:50Z)
• Advancing ESG Intelligence: An Expert-level Agent and Comprehensive Benchmark for Sustainable Finance [21.31987959023507]
  We introduce ESGAgent, a hierarchical multi-agent system empowered by a specialized toolset to generate in-depth ESG analysis.<n>We present a benchmark derived from 310 corporate sustainability reports, designed to evaluate capabilities ranging from atomic common-sense questions to the generation of integrated, in-depth analysis.
  arXiv  Detail & Related papers  (2026-01-13T15:58:29Z)
• Pharos-ESG: A Framework for Multimodal Parsing, Contextual Narration, and Hierarchical Labeling of ESG Report [9.026784135029034]
  Pharos-ESG is a framework that transforms ESG reports into structured representations through multimodal parsing, contextual nar- ration, and hierarchical labeling.<n>We release Aurora-ESG, the first large-scale public dataset of ESG re- ports, spanning Mainland China, Hong Kong, and U.S.
  arXiv  Detail & Related papers  (2025-11-20T14:41:44Z)
• Domain-Specific Data Generation Framework for RAG Adaptation [58.20906914537952]
  Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning power of large language models with external retrieval to enable domain-grounded responses.<n>We propose RAGen, a framework for generating domain-grounded question-answer-context (QAC) triples tailored to diverse RAG adaptation approaches.
  arXiv  Detail & Related papers  (2025-10-13T09:59:49Z)
• CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning [67.18702329644526]
  CoT Referring enhances model reasoning across modalities through a structured, chain-of-thought training data structure.<n>We restructure the training data to enforce a new output form, providing new annotations for existing datasets.<n>We also integrate detection and segmentation capabilities into a unified MLLM framework, training it with a novel adaptive weighted loss to optimize performance.
  arXiv  Detail & Related papers  (2025-10-03T08:50:21Z)
• Agentic Services Computing [51.50424046053763]
  We propose Agentic Services Computing, a paradigm that reimagines services as autonomous, adaptive, and collaborative agents.<n>We organize ASC around a four-phase lifecycle: Design, Deployment, Operation, and Evolution.
  arXiv  Detail & Related papers  (2025-09-29T07:29:18Z)
• MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks [56.350173737493215]
  Environmental, Social, and Governance (ESG) reports are essential for evaluating sustainability practices, ensuring regulatory compliance, and promoting financial transparency.<n>MMESGBench is a first-of-its-kind benchmark dataset to evaluate multimodal understanding and complex reasoning across structurally diverse and multi-source ESG documents.<n>MMESGBench comprises 933 validated QA pairs derived from 45 ESG documents, spanning across seven distinct document types and three major ESG source categories.
  arXiv  Detail & Related papers  (2025-07-25T03:58:07Z)
• Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation [91.17994756436259]
  Multi-agent systems (MAS) based on large language models (LLMs) have emerged as a powerful solution for dealing with complex problems across diverse domains.<n>Existing approaches are fundamentally constrained by their reliance on a template graph modification paradigm with a predefined set of agents and hard-coded interaction structures.<n>We propose ARG-Designer, a novel autoregressive model that operationalizes this paradigm by constructing the collaboration graph from scratch.
  arXiv  Detail & Related papers  (2025-07-24T09:17:41Z)
• Enhancing Retrieval for ESGLLM via ESG-CID -- A Disclosure Content Index Finetuning Dataset for Mapping GRI and ESRS [15.217878978015856]
  Climate change has intensified the need for transparency and accountability in organizational practices.<n> Frameworks like the Global Reporting Initiative (GRI) and the new European Sustainability Reporting Standards (ESRS) aim to standardize ESG reporting.<n> generating comprehensive reports remains challenging due to the considerable length of ESG documents and variability in company reporting styles.
  arXiv  Detail & Related papers  (2025-03-10T18:07:33Z)
• Optimizing Large Language Models for ESG Activity Detection in Financial Texts [0.7373617024876725]
  This paper investigates the ability of current-generation Large Language Models to identify text related to environmental activities.<n>We introduce ESG-Activities, a benchmark dataset containing 1,325 labelled text segments classified according to the EU ESG taxonomy.<n>Our experimental results show that fine-tuning on ESG-Activities significantly enhances classification accuracy.
  arXiv  Detail & Related papers  (2025-02-28T14:52:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.