cs.AINov 18, 2026

automodel: A Skill for Agentic Model Discovery

Authors: Marco Virgolin, Harry Desmond, Ester Bergantin, Giorgio Morales, John W. Sheppard, Luigi Romano, Alessandro Lucantonio

Organizations: Unlayer AI, Amsterdam, the Netherlands · Institute of Cosmology and Gravitation, University of Portsmouth, Portsmouth, UK · Department of Mathematics, University of Trento, Trento, Italy · Aston Centre for Artificial Intelligence Research and Application, Aston University, Birmingham, UK · 

Abstract

The search for better models, whether expressed as analytical equations or neural architectures, has increasingly shifted from manual design toward data-driven automation. While a multitude of algorithms exist, ranging from exhaustive search to AlphaEvolve, recent advances in general-purpose coding agents such as Claude Code and OpenAI Codex raise the question: could providing such systems with a "model discovery recipe" be enough to discover or improve models? We present automodel, an agent skill for general model discovery. With case studies in astrophysics, cardiovascular dynamics, precision agriculture, traffic flow, and vehicle tire dynamics, we show how commercial agents equipped with automodel can successfully identify novel and scientifically-relevant models. Our findings suggest that encoding model-discovery methodology as a portable agent skill can provide a simple, interactive, powerful and broadly applicable alternative to domain-specific automated discovery pipelines. The skill is available at: https://github.com/unlayer-ai/automodel.

Figures & tables

Explore similar work

CardsList
  1. EvoSkill: Automated Skill Discovery for Multi-Agent Systems

    Mar 3, 2026Salaheddin Alzubi, Noah Provenzano, Jaydon Bingham +2Agent Skill LearningLLM Agent Self-Improvement

  2. An Experimental Design Approach to Evaluating Agentic AI's Autonomous Model Discovery

    Jul 7, 2026Hao He, Xueying Liu, Chris J. Kuhlman +1AI Coding AgentsAI Agent Evaluation