Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.08676 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918288046424064 |
|---|---|
| author | Zhao, Yilei Zhang, Wentao Xiao, Lei Zheng, Yandan Liu, Mengpu Lim, Wei Yang Bryan |
| author_facet | Zhao, Yilei Zhang, Wentao Xiao, Lei Zheng, Yandan Liu, Mengpu Lim, Wei Yang Bryan |
| contents | Environmental, social, and governance (ESG) criteria are essential for evaluating corporate sustainability and ethical performance. However, professional ESG analysis is hindered by data fragmentation across unstructured sources, and existing large language models (LLMs) often struggle with the complex, multi-step workflows required for rigorous auditing. To address these limitations, we introduce ESGAgent, a hierarchical multi-agent system empowered by a specialized toolset, including retrieval augmentation, web search and domain-specific functions, to generate in-depth ESG analysis. Complementing this agentic system, we present a comprehensive three-level 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. Empirical evaluations demonstrate that ESGAgent outperforms state-of-the-art closed-source LLMs with an average accuracy of 84.15% on atomic question-answering tasks, and excels in professional report generation by integrating rich charts and verifiable references. These findings confirm the diagnostic value of our benchmark, establishing it as a vital testbed for assessing general and advanced agentic capabilities in high-stakes vertical domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_08676 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Advancing ESG Intelligence: An Expert-level Agent and Comprehensive Benchmark for Sustainable Finance Zhao, Yilei Zhang, Wentao Xiao, Lei Zheng, Yandan Liu, Mengpu Lim, Wei Yang Bryan Artificial Intelligence Environmental, social, and governance (ESG) criteria are essential for evaluating corporate sustainability and ethical performance. However, professional ESG analysis is hindered by data fragmentation across unstructured sources, and existing large language models (LLMs) often struggle with the complex, multi-step workflows required for rigorous auditing. To address these limitations, we introduce ESGAgent, a hierarchical multi-agent system empowered by a specialized toolset, including retrieval augmentation, web search and domain-specific functions, to generate in-depth ESG analysis. Complementing this agentic system, we present a comprehensive three-level 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. Empirical evaluations demonstrate that ESGAgent outperforms state-of-the-art closed-source LLMs with an average accuracy of 84.15% on atomic question-answering tasks, and excels in professional report generation by integrating rich charts and verifiable references. These findings confirm the diagnostic value of our benchmark, establishing it as a vital testbed for assessing general and advanced agentic capabilities in high-stakes vertical domains. |
| title | Advancing ESG Intelligence: An Expert-level Agent and Comprehensive Benchmark for Sustainable Finance |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2601.08676 |