Evidence-Grounded Agentic Formulation Development in an Autonomous Laboratory

Self-emulsifying drug delivery systems (SEDDS) can improve the oral bioavailability of poorly soluble drugs, but identifying high-performing formulations remains experimentally intensive. We present \andromedatwo, an agentic system that reasons over structured in-house experimental evidence and invokes computational and experimental tools to design and execute successive formulation batches. In a miniaturized automated laboratory at a matched budget, we benchmark it against \andromedaone, a probabilistic optimization model deployed across dozens of live development projects, and a wet-lab design-of-experiments (DoE) campaign. On paclitaxel, \andromedatwo achieved a 50\% high-performance hit rate versus 17\% for \andromedaone and 2\% for DoE, and identified 12 formulations meeting all four TPP criteria versus 6 and 0, respectively. Median $\mathrm{AUC}_{10\text{--}240}$ was 70.05, 11.97, and 3.49 mg$\cdot$min/mL, while maximum AUC was comparable between \andromedatwo and \andromedaone. A selected full-TPP formulation achieved an apparent effective paclitaxel loading of $19 \pm 5$\% w/w at the first FaSSIF measurement, approximately 3.3-fold higher than the 5.7\% w/w loading reported for a published paclitaxel S-SEDDS. A controlled ablation showed that access to structured in-house experimental evidence increased mean AUC by 34\%.