Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2512.21782 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915897892929536 |
|---|---|
| author | Du, Yuanqi Yu, Botao Liu, Tianyu Shen, Tony Chen, Junwu Rittig, Jan G. Sun, Kunyang Zhang, Yikun Krishnan, Aarti Zhang, Yu Rosen, Daniel Pirone, Rosali Song, Zhangde Zhou, Bo Masschelein, Cassandra Wang, Yingze Wang, Haorui Jia, Haojun Zhang, Chao Zhao, Hongyu Ester, Martin Hacohen, Nir Head-Gordon, Teresa Gomes, Carla P. Sun, Huan Duan, Chenru Schwaller, Philippe Jin, Wengong |
| author_facet | Du, Yuanqi Yu, Botao Liu, Tianyu Shen, Tony Chen, Junwu Rittig, Jan G. Sun, Kunyang Zhang, Yikun Krishnan, Aarti Zhang, Yu Rosen, Daniel Pirone, Rosali Song, Zhangde Zhou, Bo Masschelein, Cassandra Wang, Yingze Wang, Haorui Jia, Haojun Zhang, Chao Zhao, Hongyu Ester, Martin Hacohen, Nir Head-Gordon, Teresa Gomes, Carla P. Sun, Huan Duan, Chenru Schwaller, Philippe Jin, Wengong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_21782 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Accelerating Scientific Discovery with Autonomous Goal-evolving Agents Du, Yuanqi Yu, Botao Liu, Tianyu Shen, Tony Chen, Junwu Rittig, Jan G. Sun, Kunyang Zhang, Yikun Krishnan, Aarti Zhang, Yu Rosen, Daniel Pirone, Rosali Song, Zhangde Zhou, Bo Masschelein, Cassandra Wang, Yingze Wang, Haorui Jia, Haojun Zhang, Chao Zhao, Hongyu Ester, Martin Hacohen, Nir Head-Gordon, Teresa Gomes, Carla P. Sun, Huan Duan, Chenru Schwaller, Philippe Jin, Wengong Artificial Intelligence Materials Science Machine Learning Chemical Physics 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. |
| title | Accelerating Scientific Discovery with Autonomous Goal-evolving Agents |
| topic | Artificial Intelligence Materials Science Machine Learning Chemical Physics |
| url | https://arxiv.org/abs/2512.21782 |