Accelerating Scientific Discovery with Autonomous Goal-evolving Agents

TL;DR

This paper introduces SAGA, a bi-level framework using LLMs to automate the design of objectives in scientific discovery, enabling more effective exploration across various domains.

Contribution

The paper presents SAGA, a novel bi-level architecture that automates objective function design for scientific discovery agents, improving exploration and discovery outcomes.

Findings

Identified a novel antibiotic candidate with promising potency and safety.

Discovered three de novo nanobodies targeting PD-L1.

Demonstrated the framework's effectiveness across diverse scientific domains.

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 wide range of design applications, including antibiotics, nanobodies, functional DNA sequences, inorganic materials, and chemical processes. Notably, our experimental validation identifies a structurally novel hit with promising potency and safety profiles for E. coli in the antibiotic design task, and three de novo PD-L1 binders in the nanobody design task. These results suggest that automating objective formulation can substantially improve the effectiveness of scientific discovery agents.