El Agente: An Autonomous Agent for Quantum Chemistry

2025-05-05

AI Summary

High barriers to entry in computational chemistry hinder effective adoption by non-expert users. To address this, we propose a large language model (LLM)-based multi-agent system featuring a hierarchical cognitive architecture and dynamic workflow generation mechanism. This system enables end-to-end automatic translation of natural-language chemistry queries into executable quantum chemical computations (e.g., Gaussian/ORCA), supporting task decomposition, tool orchestration, file management, job submission, error localization, and in-situ debugging. A hierarchical memory framework and action-tracing logging ensure robust execution of long-horizon, multi-step tasks while preserving full interpretability. Evaluated on six undergraduate coursework problems and two real-world case studies, the system achieves >87% task success rate. It significantly improves usability, generalizability, and transparency—establishing a novel paradigm for democratizing computational chemistry.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent Communication
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Computational chemistry tools are widely used to study the behaviour of chemical phenomena. Yet, the complexity of these tools can make them inaccessible to non-specialists and challenging even for experts. In this work, we introduce El Agente Q, an LLM-based multi-agent system that dynamically generates and executes quantum chemistry workflows from natural language user prompts. The system is built on a novel cognitive architecture featuring a hierarchical memory framework that enables flexible task decomposition, adaptive tool selection, post-analysis, and autonomous file handling and submission. El Agente Q is benchmarked on six university-level course exercises and two case studies, demonstrating robust problem-solving performance (averaging>87% task success) and adaptive error handling through in situ debugging. It also supports longer-term, multi-step task execution for more complex workflows, while maintaining transparency through detailed action trace logs. Together, these capabilities lay the foundation for increasingly autonomous and accessible quantum chemistry.

Problem

• Simplifying quantum chemistry tools for non-specialists and experts
• Automating workflow generation from natural language prompts
• Enhancing error handling and multi-step task execution

Innovation

• LLM-based multi-agent system for chemistry workflows
• Hierarchical memory framework for task decomposition
• Adaptive error handling with in situ debugging