El Agente Estructural: An Artificially Intelligent Molecular Editor

2026-02-04

AI Summary

This work proposes a multimodal, natural language–driven intelligent molecular editing agent that overcomes the limitations of traditional molecular generation and editing methods, which often lack atomic-level precision and human-like intuition in controlling molecular connectivity and stereochemistry in three-dimensional space. By integrating vision–language models with a geometry-aware toolkit, the approach enables context-aware, interactive 3D molecular editing without requiring full scaffold reconstruction. It allows direct manipulation of atoms, functional groups, and stereocenters, demonstrating high chemical fidelity in tasks such as site-selective functionalization, ligand exchange, isomer interconversion, and reaction mechanism modeling. The method thus establishes a new paradigm for intuitive, precise, and chemically reasonable 3D molecular design.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: 3D Computer Vision
• Natural Language Processing: Generation

Application Category

• 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: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

We present El Agente Estructural, a multimodal, natural-language-driven geometry-generation and manipulation agent for autonomous chemistry and molecular modelling. Unlike molecular generation or editing via generative models, Estructural mimics how human experts directly manipulate molecular systems in three dimensions by integrating a comprehensive set of domain-informed tools and vision-language models. This design enables precise control over atomic or functional group replacements, atomic connectivity, and stereochemistry without the need to rebuild extensive core molecular frameworks. Through a series of representative case studies, we demonstrate that Estructural enables chemically meaningful geometry manipulation across a wide range of real-world scenarios. These include site-selective functionalization, ligand binding, ligand exchange, stereochemically controlled structure construction, isomer interconversion, fragment-level structural analysis, image-guided generation of structures from schematic reaction mechanisms, and mechanism-driven geometry generation and modification. These examples illustrate how multimodal reasoning, when combined with specialized geometry-aware tools, supports interactive and context-aware molecular modelling beyond structure generation. Looking forward, the integration of Estructural into El Agente Quntur, an autonomous multi-agent quantum chemistry platform, enhances its capabilities by adding sophisticated tools for the generation and editing of three-dimensional structures.

Problem

• molecular editing
• 3D geometry manipulation
• stereochemistry control
• functional group replacement
• atomic connectivity

Innovation

• multimodal reasoning
• geometry-aware molecular editing
• vision-language models
• stereochemistry control
• interactive molecular modeling