Abstract
Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable but can omit useful evidence from other experiments, whereas including the full experimental history produces long, redundant contexts. We introduce a simple, single-agent discovery harness built around LabBook, an agent-maintained memory that serves two complementary roles: guiding retrieval of relevant evidence from a complete experimental log and informing the generation of new solutions. At each iteration, the same agent combines its memory with retrieved evidence and jointly produces the next program and an updated LabBook. This separates complete history retention from selective context construction, without requiring an explicit population or branching search structure. On 49 Frontier-CS problems, LabBook improves the observed quality-cost trade-off over the evaluated evolutionary baselines with two backbones, while remaining competitive across nine additional mathematical, systems, and heuristic-design tasks. Code will be released at https://github.com/BoYuanVisionary/LabBook.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Yuan, B., Ye, W., Zhao, Z., Moukheiber, L., Kautz, H., Zhang, A., & Chen, Y. (2026). LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery. https://omanscience.com/en/articles/labbook-harnessing-experimental-history-for-efficient-llm-driven-discovery
MLA 9
Yuan, Bo, et al. "LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery." https://omanscience.com/en/articles/labbook-harnessing-experimental-history-for-efficient-llm-driven-discovery.
Chicago (author–date)
Yuan, Bo, Wenqian Ye, Zelin Zhao, Lama Moukheiber, Henry Kautz, Aidong Zhang, and Yongxin Chen. 2026. "LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery." https://omanscience.com/en/articles/labbook-harnessing-experimental-history-for-efficient-llm-driven-discovery.
Harvard
Yuan, B., Ye, W., Zhao, Z., Moukheiber, L., Kautz, H., Zhang, A. and Chen, Y. (2026) 'LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery', Available at: https://omanscience.com/en/articles/labbook-harnessing-experimental-history-for-efficient-llm-driven-discovery.
Vancouver
Yuan B, Ye W, Zhao Z, Moukheiber L, Kautz H, Zhang A, et al. LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery. https://omanscience.com/en/articles/labbook-harnessing-experimental-history-for-efficient-llm-driven-discovery
IEEE
B. Yuan, W. Ye, Z. Zhao, L. Moukheiber, H. Kautz, A. Zhang, and Y. Chen, "LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery," https://omanscience.com/en/articles/labbook-harnessing-experimental-history-for-efficient-llm-driven-discovery.