Detecting whether corporate sustainability disclosures truly satisfy reporting standards is essential for greenwashing-aware ESG auditing, yet existing resources rarely evaluate whether disclosures sufficiently satisfy framework metrics. We introduce MM-COMPLIANCE, a multilingual multimodal dataset aligned with SASB metrics across six languages (English, French, Japanese, Chinese, Thai, and Korean), with page-level evidence and a key completeness annotation that separates fully compliant disclosures from partial mentions. We define two tasks reflecting practical auditing workflows: Page-level Compliance Judgment and Metric-to-Page Evidence Retrieval. Our evaluated baselines primarily comprising open-source architectures, supplemented by a commercial VLM as an upper-bound reference, show moderate performance for page understanding and evidence localization, but consistently low performance on partial compliance verification and large variation across languages and industries. MM-COMPLIANCE provides a benchmark for developing framework-aware models to support rigorous ESG compliance auditing and long-term commitment tracing.

Recent advancements in large language models (LLMs) and AI systems have led to a paradigm shift in the design and optimization of complex AI workflows. By integrating multiple components, compound AI systems have become increasingly adept at performing sophisticated tasks. However, as these systems grow in complexity, new challenges arise in optimizing not only individual components but also their interactions. While traditional optimization methods such as supervised fine-tuning (SFT) and reinforcement learning (RL) remain foundational, the rise of natural language feedback introduces promising new approaches, especially for optimizing non-differentiable systems. This paper provides a systematic review of recent progress in optimizing compound AI systems, encompassing both numerical and language-based techniques. We formalize the notion of compound AI system optimization, classify existing methods along several key dimensions, and highlight open research challenges and future directions in this rapidly evolving field.