# Advancing ESG Intelligence: An Expert-level Agent and Comprehensive Benchmark for Sustainable Finance

arXiv: https://arxiv.org/abs/2601.08676 · HTML: https://mlsanity.com/paper/2601.08676/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 59 references that are in the map.
- First posted on arXiv 13 Jan 2026.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 14 of 14)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [ClimateBert: A Pretrained Language Model for Climate-Related Text](https://mlsanity.com/paper/2110.12010/) (2021)
- [FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"](https://mlsanity.com/paper/2410.03727/) (2024)
- [Correctness is not Faithfulness in RAG Attributions](https://mlsanity.com/paper/2412.18004/) (2024)
- [ESGReveal: An LLM-based approach for extracting structured data from ESG reports](https://mlsanity.com/paper/2312.17264/) (2023)
- [FinSight: Towards Real-World Financial Deep Research](https://mlsanity.com/paper/2510.16844/) (2025)
- [Towards Robust ESG Analysis Against Greenwashing Risks: Aspect-Action Analysis with Cross-Category Generalization](https://mlsanity.com/paper/2502.15821/) (2025)
- [MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks](https://mlsanity.com/paper/2507.18932/) (2025)
- [Denoising ESG: quantifying data uncertainty from missing data with Machine Learning and prediction intervals](https://mlsanity.com/paper/2407.20047/) (2024)
- [CiteCheck: Towards Accurate Citation Faithfulness Detection](https://mlsanity.com/paper/2502.10881/) (2025)

## Built on by (most cited first, 1 of 1)

- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)

## Abstract (arXiv)

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.