aiqbench analysis
El Agente F\'armaco represents a significant advancement in applying agentic AI workflows to automate complex computational drug discovery pipelines. By integrating a shared scientific memory with large language models, the system effectively reduces expert intervention while maintaining high-quality candidate generation and lower token usage compared to standard tool-calling methods. This work demonstrates how LLMs can orchestrate diverse scientific tools to scale molecular screening without sacrificing result interpretability.
El Agente F\'armaco: A Scalable AI Scientist for Drug Discovery
arXiv:2611.03832v1 Announce Type: new Abstract: Computational drug discovery offers a growing range of tools for proposing and evaluating molecules, but combining them and deciding what to do next still requires substantial expert effort. Here, we introduce El Agente F\'armaco, an AI scientist that uses modern large language model (LLM) technology to turn discovery goals expressed in everyday language into complex, scalable computational screening workflows. The agentic harness selects scientific tools, reviews their results, and adjusts subsequent steps to the target and the user's objectives. Our approach centers on a shared scientific memory: F\'armaco Atlas, which stores molecules, structures, and results together with their provenance -- a record of how they were obtained. The agent uses targeted database queries to retrieve the evidence needed for each decision. A single request can launch calculations for an entire collection of molecules, without requiring a separate LLM decision for every compound. This design limits the information the model must process as screening collections grow, while keeping the underlying results available for inspection and further analysis. The integrated tools support molecule generation, prediction of binding and molecular properties, and searches for compounds available for purchase. In a retrospective comparison with an expert-led campaign, the agent proposed chemically distinct candidates with competitive docking scores and higher calculated drug-likeness under explicitly imposed selection criteria. In a 22-task benchmark against plain tool calls and Codex, the agent achieved the highest observed mean model-judged score, with lower median cumulative token use and peak context. F\'armaco provides a foundation for flexible, scalable drug discovery workflows that connect scientific reasoning with an enduring, traceable record of computational work.
Authors:Marcel Müller, Mohammad Ghazi Vakili, Yoshihiro Ogura, Ella Ashoori, Shimeng Wang, Alessandro S. Nascimento, Eddie Calleja, Yutong Zhao, Yimeng Liu, Ella Miray Rajaonson, Aiwei Yin, Jiaru Bai, Yunheng Zou, Abraham C. Stern, Varinia Bernales, Alán Aspuru-Guzik
Abstract:Computational drug discovery offers a growing range of tools for proposing and evaluating molecules, but combining them and deciding what to do next still requires substantial expert effort. Here, we introduce El Agente Fármaco, an AI scientist that uses modern large language model (LLM) technology to turn discovery goals expressed in everyday language into complex, scalable computational screening workflows. The agentic harness selects scientific tools, reviews their results, and adjusts subsequent steps to the target and the user's objectives. Our approach centers on a shared scientific memory: Fármaco Atlas, which stores molecules, structures, and results together with their provenance -- a record of how they were obtained. The agent uses targeted database queries to retrieve the evidence needed for each decision. A single request can launch calculations for an entire collection of molecules, without requiring a separate LLM decision for every compound. This design limits the information the model must process as screening collections grow, while keeping the underlying results available for inspection and further analysis. The integrated tools support molecule generation, prediction of binding and molecular properties, and searches for compounds available for purchase. In a retrospective comparison with an expert-led campaign, the agent proposed chemically distinct candidates with competitive docking scores and higher calculated drug-likeness under explicitly imposed selection criteria. In a 22-task benchmark against plain tool calls and Codex, the agent achieved the highest observed mean model-judged score, with lower median cumulative token use and peak context. Fármaco provides a foundation for flexible, scalable drug discovery workflows that connect scientific reasoning with an enduring, traceable record of computational work.
Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Biomolecules (q-bio.BM)
arXiv:2611.03832 [cs.AI]
(or arXiv:2611.03832v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2611.03832 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 321 words
Related coverage
Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery
arXiv · Oct 7, 2026
DISCERN: Can AI Agents Work Like Scientists and Guide Discovery?
arXiv · Sep 29, 2026
A concrete vision: Saint-Gobain and Microsoft Discovery build for the future
Microsoft · Oct 20, 2026
Accelerating scientific discovery with Co-Scientist
Nature · May 19, 2026