cs.AINov 4, 2026

KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Tasks

Authors: Zi-Jian Cheng, Weiming Wu, Jie Meng, Zhen Peng, Shan Huang, Qun Li, Guobing Wu, Lan-Zhe Guo

Organizations: National Key Laboratory for Novel Software Technology, Nanjing University · School of Intelligence Science and Technology, Nanjing University · DiDichuxing Co. Ltd, Beijing, China

Abstract

Liability adjudication tasks (e.g., legal charge determination) require analyzing event descriptions against domain-specific skills to determine whether a party should bear liability. While Large Language Models (LLMs) have shown promise in this area by leveraging executable skills for interpretable reasoning, existing approaches face three critical limitations: skill libraries become stale as real-world scenarios dynamically evolve, skill descriptions often suffer from a semantic execution gap where LLMs deviate from intended expert logic, and growing skill collections exceed context budgets causing critical skill omission. To address these challenges, we propose 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 selection. Experiments across ride-hailing adjudication, legal liability determination, and logical reasoning judgment demonstrate that KDASO significantly outperforms current general-purpose and domain-specific baselines. KDASO further achieves 8.96% improvement when transferring skills to concept-similar scenarios and maintains consistent performance gains through continuous optimization, underscoring the high transferability and stability of generated skills.

Figures & tables

Appendix figures & tables17 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Skill Adapter: Personalized Modification and Online Routing of General-Purpose Skills

    Nov 12, 2026Qijia Zhuang, Yanyin Gou, Wenbin Ma +1LLM Agent Skill RetrievalLLM Agent Routing

  2. Prompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions

    Sep 29, 2026Bo Ni, Li Li, Ryan A. Rossi +2LLM Agent Skill LearningLanguage Model Self-Improvement

  3. Agentic Skill Optimization over Lie Algebroids

    Jul 13, 2026Sridhar MahadevanLarge Language Model-Guided OptimizationLLM Agent Skill Learning