AI Insight
OptScientist is a new automated framework that discovers symbolic optimization laws directly from data by combining a model that infers optimization problems with an AI agent system that integrates scientific literature and suggests new experiments. When tested on OptFeynman, a benchmark of 99 physics-derived optimization problems, it successfully recovered correct laws in over 80% of cases and outperformed existing machine learning and symbolic baselines. The system also demonstrated effectiveness on real-world problems including human decision-making under risk and central bank monetary policy, achieving competitive predictions with fewer parameters than alternative approaches.
Why it matters
This framework could accelerate scientific discovery across multiple disciplines by automatically identifying the optimization principles underlying observed phenomena, rather than just fitting equations to data. The approach has potential applications in physics, biology, behavioral science, and social sciences where phenomena emerge from optimization processes.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Abstract: Many scientific phenomena are best understood as outcomes of underlying optimization problems, yet automated scientific discovery has largely focused on recovering equations that describe observed input-output patterns. We introduce OptScientist, a novel automated framework for discovering compact symbolic optimization laws directly from data. OptScientist comprises (i) a model that infers symbolic optimization problems by first learning to represent data as an optimization problem and then extracting its symbolic form, and (ii) an LLM agentic system embedding the model in a discovery process that integrates theoretical priors from scientific literature, discovers candidate laws, abstracts their underlying mechanisms, and suggests new data to collect. We first evaluate OptScientist on OptFeynman, a novel benchmark of 99 physics-derived optimization problems, where OptScientist recovers ground-truth laws for over 80% of the problems and remains robust to noisy contextual information, while substantially outperforming machine-learning, symbolic, and LLM-based model-discovery baselines. On human risky choice and central-bank monetary policy, OptScientist discovers compact symbolic optimization laws that achieve held-out predictive performance competitive with leading baselines, while using few parameters and substantially fewer tokens than LLM baselines. Overall, OptScientist extends automated scientific discovery to uncovering optimization laws that generate observed phenomena, enabling automated theory building across the physical, biological, behavioral, and social sciences.
Source: OptScientist: Automated Discovery of Optimization Laws