MEMIG: Self-evolving Memory Construction for Antibody Optimization
This work argues that agent memory for biomolecule optimization should instead be indexable, quantitative, and structured, and introduces MEMIG, a memory construction framework that addresses each insight with a domain-grounded identifier and accumulates the quantitative effect measured by a property oracle.
Yun-Hui Jang, Zach Wang, Jai Doshi et al.
· 0 citations