LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery

Excerpt

arXiv:2610.00675v1 Announce Type: new 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