Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

OpenQlaw: An Agentic AI Assistant for Analysis of 2D Quantum Materials

Sankalp Pandey, Xuan-Bac Nguyen, Hoang-Quan Nguyen, Tim Faltermeier, Nicholas Borys, Hugh Churchill, Khoa Luu

Abstract

The transition from optical identification of 2D quantum materials to practical device fabrication requires dynamic reasoning beyond the detection accuracy. While recent domain-specific Multimodal Large Language Models (MLLMs) successfully ground visual features using physics-informed reasoning, their outputs are optimized for step-by-step cognitive transparency. This yields verbose candidate enumerations followed by dense reasoning that, while accurate, may induce cognitive overload and lack immediate utility for real-world interaction with researchers. To address this challenge, we introduce OpenQlaw, an agentic orchestration system for analyzing 2D materials. The architecture is built upon NanoBot, a lightweight agentic framework inspired by OpenClaw, and QuPAINT, one of the first Physics-Aware Instruction Multi-modal platforms for Quantum Material Discovery. This allows accessibility to the lab floor via a variety of messaging channels. OpenQlaw allows the core Large Language Model (LLM) agent to orchestrate a domain-expert MLLM,with QuPAINT, as a specialized node, successfully decoupling visual identification from reasoning and deterministic image rendering. By parsing spatial data from the expert, the agent can dynamically process user queries, such as performing scale-aware physical computation or generating isolated visual annotations, and answer in a naturalistic manner. Crucially, the system features a persistent memory that enables the agent to save physical scale ratios (e.g., 1 pixel = 0.25 μm) for area computations and store sample preparation methods for efficacy comparison. The application of an agentic architecture, together with the extension that uses the core agent as an orchestrator for domain-specific experts, transforms isolated inferences into a context-aware assistant capable of accelerating high-throughput device fabrication.

OpenQlaw: An Agentic AI Assistant for Analysis of 2D Quantum Materials

Abstract

The transition from optical identification of 2D quantum materials to practical device fabrication requires dynamic reasoning beyond the detection accuracy. While recent domain-specific Multimodal Large Language Models (MLLMs) successfully ground visual features using physics-informed reasoning, their outputs are optimized for step-by-step cognitive transparency. This yields verbose candidate enumerations followed by dense reasoning that, while accurate, may induce cognitive overload and lack immediate utility for real-world interaction with researchers. To address this challenge, we introduce OpenQlaw, an agentic orchestration system for analyzing 2D materials. The architecture is built upon NanoBot, a lightweight agentic framework inspired by OpenClaw, and QuPAINT, one of the first Physics-Aware Instruction Multi-modal platforms for Quantum Material Discovery. This allows accessibility to the lab floor via a variety of messaging channels. OpenQlaw allows the core Large Language Model (LLM) agent to orchestrate a domain-expert MLLM,with QuPAINT, as a specialized node, successfully decoupling visual identification from reasoning and deterministic image rendering. By parsing spatial data from the expert, the agent can dynamically process user queries, such as performing scale-aware physical computation or generating isolated visual annotations, and answer in a naturalistic manner. Crucially, the system features a persistent memory that enables the agent to save physical scale ratios (e.g., 1 pixel = 0.25 μm) for area computations and store sample preparation methods for efficacy comparison. The application of an agentic architecture, together with the extension that uses the core agent as an orchestrator for domain-specific experts, transforms isolated inferences into a context-aware assistant capable of accelerating high-throughput device fabrication.
Paper Structure (21 sections, 4 figures)

This paper contains 21 sections, 4 figures.

Table of Contents

  1. Introduction
  2. Limitations of Object Detectors
  3. Interpretability with MLLMs
  4. Contributions of this Work
  5. The OpenQlaw Framework
  6. Agentic Orchestration Loop
  7. Material Domain Expert (QuPAINT)
  8. Deterministic Execution Tools
  9. Implementation Details
  10. Core Engine
  11. Tool Schema and Prompt Engineering
  12. State Management and Execution
  13. Results and Discussion
  14. Baseline Results with QuPAINT
  15. OpenQlaw Results
  16. ...and 6 more sections

Figures (4)

  • Figure 1: The proposed OpenQlaw framework.
  • Figure 2: Baseline output from the Material Domain Expert (QuPAINT) illustrating the verbose cognitive traces and mass raw coordinate enumeration.
  • Figure 3: OpenQlaw framework executing a conversational workflow via WhatsApp, showcasing concise natural language responses and deterministic execution.
  • Figure 4: Demonstration of OpenQlaw's memory, storing cached sample preparation methods and using saved physical scaling ratios for downstream calculations