推进ESG智能：一个专家级代理和全面的可持续金融基准
Advancing ESG Intelligence: An Expert-level Agent and Comprehensive Benchmark for Sustainable Finance
AI总结：
本文提出ESGAgent多代理系统及三级基准，通过高准确率在原子问题回答和专业报告生成中超越现有LLMs，为可持续金融领域提供关键评估工具。
摘要：
环境、社会和治理（ESG）标准对于评估企业可持续性和道德表现至关重要。然而，专业ESG分析受到跨非结构化来源的数据碎片化的阻碍，现有大型语言模型（LLMs）往往难以处理复杂、多步骤的工作流程所需严格审计。为了解决这些限制，我们引入了ESGAgent，一个由专用工具集赋能的分层多代理系统，包括检索增强、网络搜索和领域特定功能，以生成深入的ESG分析。此外，我们提出了一个全面的三级基准，源自310份企业可持续性报告，旨在评估从原子常识问题到生成整合、深入分析的能力范围。实证评估显示，ESGAgent在原子问题回答任务上的平均准确率为84.15%，在专业报告生成方面通过整合丰富的图表和可验证的参考文献表现出色。这些发现证实了我们基准的诊断价值，使其成为评估一般和高级代理能力在高风险垂直领域的重要测试平台。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
