KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Tasks
This work proposes Knowledge-Data Dual-Driven Automated Skill Optimization (KDASO), which continuously evolves a skill library through neighborhood-conditioned induction from recent adjudication data, execution-aligned refinement based on LLM trajectory analysis, and context-budgeted routing for scalable skill selectio...
Zi-Jian Cheng, Wei-Ming Wu, J. Meng et al.
· 0 citations