PowerDAG: Reliable Agentic AI System for Automating Distribution Grid Analysis
It addresses reliability issues in agentic AI for engineering workflows, offering incremental improvements in a domain-specific context.
This paper tackles the reliability challenges in automating complex distribution-grid analysis workflows with agentic AI systems, achieving a 100% success rate with GPT-5.2 and 94.4-96.7% with smaller models, outperforming baselines by 6-50 percentage points.
This paper introduces PowerDAG, an agentic AI system for automating complex distribution-grid analysis. We address the reliability challenges of state-of-the-art agentic systems in automating complex engineering workflows by introducing two innovative active mechanisms: (i) \textbf{adaptive retrieval}, which uses a similarity-decay cutoff algorithm to dynamically select the most relevant annotated exemplars as context, and (ii) \textbf{just-in-time (JIT) supervision}, which actively intercepts and corrects tool-usage violations during execution. On a benchmark of unseen distribution grid analysis queries, PowerDAG achieves a 100\% success rate with GPT-5.2 and 94.4--96.7\% with smaller open-source models, outperforming base ReAct (41--88\%), LangChain (30--90\%), and CrewAI (9--41\%) baselines by margins of 6--50 percentage points.