Newest papers

OptScientist: Automated Discovery of Optimization Laws

Ma ZhenYao, Yue Liang, Jian-Qiao Zhu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28562 · cited by 0 works (OpenAlex) · open-access PDF

Korean

많은 생물학적 현상은 기본적인 최적화 문제의 결과로 가장 잘 이해되지만 자동화 된 과학적 발견은 관찰 된 입력 출력 패턴을 묘사하는 균형을 복구하는 데 중점을 두었습니다. 우리는 OptScientist를 소개합니다. Compact Symbolic Optimization Laws를 데이터에서 직접 발견하기위한 새로운 자동화 된 프레임 워크입니다. OptScientist는 (i) 데이터를 최적화 문제로 표현하기 위해 데이터를 처음으로 배우고 상징적 형태를 추출함으로써 상징적 최적화 문제를 추출하는 모델을 포함합니다. 그리고 (ii) 과학 문학에서 이론적 원인을 통합하는 발견 과정에 모델을 포함하는 LLM 에이전트 시스템을 소개합니다. OptScientist는 과학적 최적화 프로세스를 통합하여 과학적

Machine translation (Meta M2M100); the English original follows.

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Embedding, Benchmark (surveying), Process (computing), Optimization problem, Artificial intelligence

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange