Accelerating Scientific Discovery with Autonomous Goal-evolving Agents

Yuanqi Du, Botao Yu, Tianyu Liu, Tony Shen, Junwu Chen, Jan G. Rittig, Kunyang Sun, Yikun Zhang, Cassandra Masschelein, Yingze Wang, Haorui Wang, Haojun Jia, Chao Zhang, Hongyu Zhao, Martin Ester, Teresa Head-Gordon, Carla P Gomes, Huan Sun, Chenru Duan, Philippe Schwaller et al. (1 additional authors not shown)

Track: Tiny / short paper (2-4 pages)

Keywords: AI Agents, DNA Sequence Design, nanobody design

TL;DR: An AI Agent system for general design problem

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 solution optimization under the current objectives. This bi-level design enables systematic exploration of the space of objectives and their trade-offs, rather than treating them as fixed inputs. We demonstrate the framework through a broad spectrum of design applications, including antibiotic drug discovery, novel inorganic materials, functional DNA sequences, nanobodies, and chemical separation processes, showing that automating objective formulation can substantially improve the effectiveness of scientific discovery agents.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Submission Number: 19