Accelerating Scientific Discovery with Autonomous Goal-evolving Agents
This addresses the challenge of improving scientific discovery agents for researchers by automating objective formulation, though it appears incremental as it builds on existing agent frameworks.
The paper tackles the problem of automating objective function design for scientific discovery agents, which are typically limited by imperfect proxies, by introducing SAGA, a bi-level architecture that proposes and optimizes new objectives, and demonstrates its effectiveness across applications like antibiotic and materials design.
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 are only imperfect proxies. We argue that automating objective function design is a central, yet unmet requirement for scientific discovery agents. In this work, we introduce the Scientific Autonomous Goal-evolving Agent (SAGA) to amend 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 applications, including antibiotic design, inorganic materials design, functional DNA sequence design, and chemical process design, showing that automating objective formulation can substantially improve the effectiveness of scientific discovery agents.