Environmental, social, and governance (ESG) criteria are essential for evaluating corporate sustainability, yet professional ESG analysis is hindered by data fragmentation and complex multi-step workflows. Existing ESG benchmarks rely on LLM-generated questions that often suffer from semantic ambiguity, limiting their diagnostic reliability. We introduce ESGAgent, a hierarchical multi-agent system with a domain-oriented toolset for automating end-to-end ESG workflows, and a three-level benchmark derived from 310 corporate sustainability reports, featuring expert-sourced questions with verified, unambiguous answers at Levels 1-2 and full report generation at Level 3. Evaluations across 20 state-of-the-art closed-source LLMs show that ESGAgent achieves 84.15% accuracy on Levels 1-2, surpassing the strongest baseline by 3.26 points, and produces Level 3 reports with higher factual consistency and analytical depth than commercial deep research systems, validated by both multi-LLM judging and human expert evaluation, showing a robust alignment (Pearson r=0.551).

Semi-supervised learning has been an important approach to address challenges in extracting entities and relations from limited data. However, current semi-supervised works handle the two tasks (i.e., Named Entity Recognition and Relation Extraction) separately and ignore the cross-correlation of entity and relation instances as well as the existence of similar instances across unlabeled data. To alleviate the issues, we propose Jointprop, a Heterogeneous Graph-based Propagation framework for joint semi-supervised entity and relation extraction, which captures the global structure information between individual tasks and exploits interactions within unlabeled data. Specifically, we construct a unified span-based heterogeneous graph from entity and relation candidates and propagate class labels based on confidence scores. We then employ a propagation learning scheme to leverage the affinities between labelled and unlabeled samples. Experiments on benchmark datasets show that our framework outperforms the state-of-the-art semi-supervised approaches on NER and RE tasks. We show that the joint semi-supervised learning of the two tasks benefits from their codependency and validates the importance of utilizing the shared information between unlabeled data.