El Agente: An Autonomous Agent for Quantum Chemistry

TL;DR

El Agente Q is an innovative multi-agent system leveraging large language models to automate and simplify quantum chemistry workflows, making advanced computational tools more accessible and autonomous for users.

Contribution

This work introduces El Agente Q, a novel hierarchical, multi-agent architecture that dynamically generates, executes, and manages quantum chemistry tasks from natural language prompts.

Findings

Achieved over 87% task success rate across benchmarks.

Demonstrated robust error handling and in situ debugging.

Supported complex multi-step workflows with transparency.

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.