PowerDAG: Reliable Agentic AI System for Automating Distribution Grid Analysis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915949021495296 |
|---|---|
| author | Badmus, Emmanuel O. Pandey, Amritanshu |
| author_facet | Badmus, Emmanuel O. Pandey, Amritanshu |
| contents | 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: adaptive retrieval, which uses a similarity-decay cutoff algorithm to dynamically select the most relevant annotated exemplars as context, and 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_17418 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PowerDAG: Reliable Agentic AI System for Automating Distribution Grid Analysis Badmus, Emmanuel O. Pandey, Amritanshu Systems and Control 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: adaptive retrieval, which uses a similarity-decay cutoff algorithm to dynamically select the most relevant annotated exemplars as context, and 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. |
| title | PowerDAG: Reliable Agentic AI System for Automating Distribution Grid Analysis |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2603.17418 |