[2512.21782] Accelerating Scientific Discovery with Autonomous Goal-evolving Agents

Computer Science > Artificial Intelligence arXiv:2512.21782 (cs) [Submitted on 25 Dec 2025 (v1), last revised 30 Mar 2026 (this version, v2)] Title:Accelerating Scientific Discovery with Autonomous Goal-evolving Agents Authors:Yuanqi Du, Botao Yu, Tianyu Liu, Tony Shen, Junwu Chen, Jan G. Rittig, Kunyang Sun, Yikun Zhang, Aarti Krishnan, Yu Zhang, Daniel Rosen, Rosali Pirone, Zhangde Song, Bo Zhou, Cassandra Masschelein, Yingze Wang, Haorui Wang, Haojun Jia, Chao Zhang, Hongyu Zhao, Martin Ester, Nir Hacohen, Teresa Head-Gordon, Carla P. Gomes, Huan Sun, Chenru Duan, Philippe Schwaller, Wengong Jin View a PDF of the paper titled Accelerating Scientific Discovery with Autonomous Goal-evolving Agents, by Yuanqi Du and 27 other authors View PDF HTML (experimental) Abstract:There has been unprecedented interest in developing agents that expand the boundary of scientific discovery, primarily by optimizing quantitative objective functions specified by scientists. However, for grand challenges in science, these objectives may only be imperfect proxies. We argue that automating objective function design is a central, yet unmet need for scientific discovery agents. In this work, we introduce the Scientific Autonomous Goal-evolving Agent (SAGA) to address this challenge. SAGA employs a bi-level architecture in which an outer loop of LLM agents analyzes optimization outcomes, proposes new objectives, and converts them into computable scoring functions, while an inner loop performs so...