Neuro-Symbolic Agents for Regulated Process Automation: Challenges and Research Agenda
For researchers in neuro-symbolic AI and developers of LLM agents in regulated industries, this paper outlines a research agenda for integrating compliance into agent architecture.
The paper argues that symbolic structures like regulations and compliance constraints should be core architectural components for LLM-based agents in regulated industries, proposing compliance-by-construction to prevent control-flow violations while guardrails catch semantic errors. It identifies neuro-symbolic research challenges for this paradigm.
LLM-based agents are entering regulated industries where they automate judgment intensive quality management processes. We argue that symbolic structures already embedded in these domains, including regulations, typed process models, and compliance constraints, should be treated not merely as external monitoring mechanisms but as core architectural components that shape the agent's decision-making and behavior. We propose compliance-by-construction as a complementary paradigm to guardrail-based monitoring: a structural foundation that prevents control-flow violations, while guardrails remain essential for catching semantic errors. We identify a structured set of neuro-symbolic research challenges on foundational and capability level and show that addressing them jointly enables compliance-by-construction. We call on the neuro-symbolic community to engage with regulated process automation as a high impact research domain.