Abstract for: SYMBIOSIS: Systems Thinking and Machine Intelligence for Better Outcomes in Society

Systems Thinking is critical in domains such as healthcare, criminal Justice, and social policy, where factors influencing outcomes are deeply interconnected via feedback loops. Despite its utility, Systems Thinking has been limited by accessibility challenges. Models in System dynamics, while valuable, are often stored in isolated repositories, and the tools required to access and use these models are proprietary, requiring specialized knowledge that many community practitioners lack. We developed a custom XMILE parser and leveraged it to process research papers in publicly available databases to bootstrap the platform. We then developed a generative co-pilot that translates complex systems representations - such as causal loop and stock-flow diagrams - into natural language (and vice-versa), allowing users to explore and build models without extensive technical training. This was packaged into an interactive platform. Our AI-powered framework and platform increases the accessibility and usability of Systems Thinking for addressing societal challenges. Our work offers a centralized repository of systems thinking models, categorized by SDGs, and a generative AI co-pilot to translate between diagrammatic and natural language representations By making Systems Thinking frameworks more accessible and user-friendly, SYMBIOSIS aims to serve as a foundational step to unlock future research into responsible and society-centered AI that better integrates societal context by leveraging systems thinking frameworks and causal modeling methods.